Add Sentence Transformers usage (#1)

- Add Sentence Transformers usage (82f6991b0f0c597cfb36100b847a478cf374f07e)
- Simplify the Sentence Transformers section intro (0f284dd50af8e91528dd9a2e9f83bc1571e3c3f4)


Co-authored-by: Tom Aarsen <tomaarsen@users.noreply.huggingface.co>

README.md

@@ -2,6 +2,7 @@
 tags:
 - ColBERT
 - PyLate
+- multi-vector
 - sentence-transformers
 - sentence-similarity
 - embeddings
@@ -1034,6 +1035,40 @@ ColBERT(
 ```
 
 ## Usage
+
+### Sentence Transformers
+
+This model can be used with [Sentence Transformers](https://www.sbert.net/) as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
+
+```bash
+pip install "sentence-transformers>=6.0.1"
+```
+
+```python
+from sentence_transformers import MultiVectorEncoder
+
+model = MultiVectorEncoder("lightonai/ColBERT-Zero-unsupervised")
+
+query = "Which planet is known as the Red Planet?"
+documents = [
+    "Venus is often called Earth's twin because of its similar size and proximity.",
+    "Mars, known for its reddish appearance, is often referred to as the Red Planet.",
+    "Jupiter, the largest planet in our solar system, has a prominent red spot.",
+    "Saturn, famous for its rings, is sometimes mistaken for the Red Planet.",
+]
+
+query_embeddings = model.encode_query(query)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings[0].shape)
+# torch.Size([16, 128]) torch.Size([19, 128])
+
+# MaxSim late-interaction scoring (higher is more relevant)
+scores = model.similarity(query_embeddings, document_embeddings)
+print(scores)
+# tensor([[ 8.3235, 11.3196,  9.9448, 10.3868]], device='cuda:0')
+```
+
+### PyLate
 First install the PyLate library:
 
 ```bash

config_sentence_transformers.json

@@ -5,6 +5,12 @@
     "transformers": "4.48.3",
     "pytorch": "2.6.0"
   },
+  "requirements": {
+    "sentence-transformers": {
+      "specifier": ">=6.0.1",
+      "reason": "earlier versions encode this model's queries as \"search_query: ...\" instead of \"[Q] search_query: ...\", dropping the [Q] / [D] markers it was trained with and changing the embeddings."
+    }
+  },
   "prompts": {
     "query": "search_query: ",
     "document": "search_document: "