sentence_transformers_support (#1)

- Add support for Sentence Transformer (6da74ca1f33306288d1c05b67d283393d6867906)
- Adapt to the new naming of IDF (b4f72ca312ca0573d19ca5305f9776ceac8f0c69)

README.md

@@ -9,6 +9,13 @@ tags:
 - passage-retrieval
 - document-expansion
 - bag-of-words
+- sentence-transformers
+- sparse-encoder
+- sparse
+- asymmetric
+- inference-free
+pipeline_tag: feature-extraction
+library_name: sentence-transformers
 ---
 
 # opensearch-neural-sparse-encoding-doc-v3-gte
@@ -40,6 +47,46 @@ The training datasets includes MS MARCO, eli5_question_answer, squad_pairs, Wiki
 
 OpenSearch neural sparse feature supports learned sparse retrieval with lucene inverted index. Link: https://opensearch.org/docs/latest/query-dsl/specialized/neural-sparse/. The indexing and search can be performed with OpenSearch high-level API.
 
+## Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+
+```python
+from sentence_transformers.sparse_encoder import SparseEncoder
+
+# Download from the 🤗 Hub
+model = SparseEncoder("opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill")
+
+query = "What's the weather in ny now?"
+document = "Currently New York is rainy."
+
+query_embed = model.encode_query(query)
+document_embed = model.encode_document(document)
+
+sim = model.similarity(query_embed, document_embed)
+print(f"Similarity: {sim}")
+# Similarity: tensor([[12.5747]])
+
+decoded_query = model.decode(query_embed)
+decoded_document = model.decode(document_embed)
+
+for i in range(len(decoded_query)):
+    query_token, query_score = decoded_query[i]
+    doc_score = next((score for token, score in decoded_document if token == query_token), 0)
+    if doc_score != 0:
+        print(f"Token: {query_token}, Query score: {query_score:.4f}, Document score: {doc_score:.4f}")
+
+# Token: ny, Query score: 5.7729, Document score: 0.9703
+# Token: weather, Query score: 4.5684, Document score: 1.0387
+# Token: now, Query score: 3.5895, Document score: 0.5861
+# Token: in, Query score: 0.4989, Document score: 0.2494
+```
 
 ## Usage (HuggingFace)
 This model is supposed to run inside OpenSearch cluster. But you can also use it outside the cluster, with HuggingFace models API. 

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SparseEncoder",
+  "__version__": {
+    "sentence_transformers": "5.0.0",
+    "transformers": "4.50.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "dot"
+}

document_1_SpladePooling/config.json

@@ -0,0 +1,5 @@
+{
+    "pooling_strategy": "max",
+    "activation_function": "log1p_relu",
+    "word_embedding_dimension": null
+}

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Router"
+  }
+]

query_0_SparseStaticEmbedding/config.json

@@ -0,0 +1,3 @@
+{
+    "frozen": false
+}

query_0_SparseStaticEmbedding/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711ec64837a7962d2ae106996079782b7ee87860089a0b2348bf7cb840f252d3
+size 122168

query_0_SparseStaticEmbedding/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

query_0_SparseStaticEmbedding/tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

router_config.json

@@ -0,0 +1,20 @@
+{
+    "types": {
+        "query_0_SparseStaticEmbedding": "sentence_transformers.sparse_encoder.models.SparseStaticEmbedding.SparseStaticEmbedding",
+        "": "sentence_transformers.sparse_encoder.models.MLMTransformer.MLMTransformer",
+        "document_1_SpladePooling": "sentence_transformers.sparse_encoder.models.SpladePooling.SpladePooling"
+    },
+    "structure": {
+        "query": [
+            "query_0_SparseStaticEmbedding"
+        ],
+        "document": [
+            "",
+            "document_1_SpladePooling"
+        ]
+    },
+    "parameters": {
+        "default_route": "document",
+        "allow_empty_key": true
+    }
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}