Add Sentence Transformers compatibility (#1)

- Integrate with Sentence Transformers (8a96ae29be741908f0f3c15807a132e34d38e44e)
- Remove query/document mention (9b487e658a646ae0203e0970c3f3f537e33b4c07)
- Add default "Document: " prompt (f7f4fb8066c59a9752deed2257ea367d8889aa7a)
- Update README snippet results using new prompt (9fda0b7ae095b62ca1acfac8fc8034ea66e2f16b)

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

README.md

@@ -60,6 +60,43 @@ The following Python packages are required:
 
 </details>
 
+<details>
+  <summary>via <a href="https://sbert.net/">sentence-transformers</a></summary>
+
+```python
+from sentence_transformers import SentenceTransformer
+import torch
+
+model = SentenceTransformer(
+    "jinaai/jina-embeddings-v5-text-small-clustering",
+    model_kwargs={"dtype": torch.bfloat16},  # Recommended for GPUs
+    config_kwargs={"_attn_implementation": "flash_attention_2"},  # Recommended but optional
+)
+# Optional: set truncate_dim in encode() to control embedding size
+
+texts = [
+    "We propose a novel neural network architecture for image segmentation.",
+    "This paper analyzes the effects of monetary policy on inflation.",
+    "Our method achieves state-of-the-art results on object detection benchmarks.",
+    "We study the relationship between interest rates and housing prices.",
+    "A new attention mechanism is introduced for visual recognition tasks.",
+]
+
+# Encode texts
+embeddings = model.encode(texts)
+print(embeddings.shape)
+# (5, 1024)
+
+similarity = model.similarity(embeddings, embeddings)
+print(similarity)
+# tensor([[1.0000, 0.2983, 0.8631, 0.3098, 0.9106],
+#         [0.2983, 1.0000, 0.3257, 0.8041, 0.3201],
+#         [0.8631, 0.3257, 1.0000, 0.3263, 0.9007],
+#         [0.3098, 0.8041, 0.3263, 1.0000, 0.3122],
+#         [0.9106, 0.3201, 0.9007, 0.3122, 1.0000]])
+```
+</details>
+
 <details>
   <summary>via <a href="https://github.com/vllm-project/vllm">vLLM</a></summary>
 

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+    "__version__": {
+      "sentence_transformers": "5.1.2",
+      "transformers": "4.57.0",
+      "pytorch": "2.8.0"
+    },
+    "prompts":{
+      "query": "",
+      "document": "Document: "
+    },
+    "default_prompt_name": "document",
+    "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]