Update README.md

README.md

@@ -4,4 +4,76 @@ library_name: transformers.js
 
 https://huggingface.co/BAAI/bge-large-en-v1.5 with ONNX weights to be compatible with Transformers.js.
 
+## Usage (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) using:
+```bash
+npm i @xenova/transformers
+```
+
+You can then use the model to compute embeddings, as follows:
+
+```js
+import { pipeline } from '@xenova/transformers';
+
+// Create a feature-extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Xenova/bge-large-en-v1.5');
+
+// Compute sentence embeddings
+const texts = [ 'Hello world.', 'Example sentence.'];
+const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
+console.log(embeddings);
+// Tensor {
+//   dims: [ 2, 1024 ],
+//   type: 'float32',
+//   data: Float32Array(2048) [ 0.03169844672083855,  0.011085662990808487, ... ],
+//   size: 2048
+// }
+
+console.log(embeddings.tolist()); // Convert embeddings to a JavaScript list
+// [
+//   [ 0.03169844672083855, 0.011085662990808487, 0.030054178088903427, ... ],
+//   [ 0.009418969973921776, -0.024539148434996605, 0.036459196358919144, ... ]
+// ]
+```
+
+You can also use the model for retrieval. For example:
+```js
+import { pipeline, cos_sim } from '@xenova/transformers';
+
+// Create a feature-extraction pipeline
+const extractor = await pipeline('feature-extraction', 'Xenova/bge-large-en-v1.5');
+
+// List of documents you want to embed
+const texts = [
+    'Hello world.',
+    'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.',
+    'I love pandas so much!',
+];
+
+// Compute sentence embeddings
+const embeddings = await extractor(texts, { pooling: 'mean', normalize: true });
+
+// Prepend recommended query instruction for retrieval.
+const query_prefix = 'Represent this sentence for searching relevant passages: '
+const query = query_prefix + 'What is a panda?';
+const query_embeddings = await extractor(query, { pooling: 'mean', normalize: true });
+
+// Sort by cosine similarity score
+const scores = embeddings.tolist().map(
+    (embedding, i) => ({
+        id: i,
+        score: cos_sim(query_embeddings.data, embedding),
+        text: texts[i],
+    })
+).sort((a, b) => b.score - a.score);
+console.log(scores);
+// [
+//   { id: 1, score: 0.7671812872502833, text: 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.' },
+//   { id: 2, score: 0.7219157959783322, text: 'I love pandas so much!' },
+//   { id: 0, score: 0.5109676329796601, text: 'Hello world.' }
+// ]
+```
+
+
 Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).