Add Sentence Transformers usage

README.md

@@ -8,6 +8,8 @@ language:
 pipeline_tag: sentence-similarity
 tags:
 - ColBERT
+- multi-vector
+- sentence-transformers
 base_model:
 - cl-tohoku/bert-base-japanese-v3
 license: mit
@@ -163,6 +165,36 @@ RAG.search(query="What animation studio did Miyazaki found?")
 ```
 
 
+## Sentence Transformers
+
+As of [Sentence Transformers](https://www.sbert.net/) v6.0.0, this model can also be loaded directly as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
+
+```bash
+pip install "sentence-transformers>=6.0.0" fugashi unidic-lite
+```
+
+```python
+from sentence_transformers import MultiVectorEncoder
+
+model = MultiVectorEncoder("bclavie/JaColBERT")
+
+query = "日本で一番高い山は何ですか？"
+documents = [
+    "富士山は日本で最も高い山で、標高は3776メートルです。",
+    "東京は日本の首都で、世界最大の都市圏の一つです。",
+]
+
+query_embeddings = model.encode_query(query)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings[0].shape)
+# torch.Size([32, 128]) torch.Size([21, 128])
+
+# MaxSim late-interaction scoring (higher is more relevant)
+scores = model.similarity(query_embeddings, document_embeddings)
+print(scores)
+# tensor([[28.1927, 16.7800]], device='cuda:0')
+```
+
 # Citation
 
 If you'd like to cite this work, please cite the technical report: