Add pretrained model information for neural sparse (#5355)

* add pretrained model for neural sparse

Signed-off-by: xinyual <xinyual@amazon.com>

* change typo error

Signed-off-by: xinyual <xinyual@amazon.com>

* Apply suggestions from code review

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/ml-framework.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/ml-framework.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: xinyual <74362153+xinyual@users.noreply.github.com>

* Update _ml-commons-plugin/ml-framework.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: xinyual <74362153+xinyual@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: xinyual <74362153+xinyual@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _search-plugins/neural-sparse-search.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Co-authored-by: Nathan Bower <nbower@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/ml-framework.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update pretrained-models.md

Change description and name in the sparse encoding doc model example

Signed-off-by: xinyual <74362153+xinyual@users.noreply.github.com>

* Update _search-plugins/neural-sparse-search.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Update _ml-commons-plugin/pretrained-models.md

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

---------

Signed-off-by: xinyual <xinyual@amazon.com>
Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Signed-off-by: xinyual <74362153+xinyual@users.noreply.github.com>
Co-authored-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>
Co-authored-by: Nathan Bower <nbower@amazon.com>

_ml-commons-plugin/ml-framework.md

@@ -26,12 +26,21 @@ To upload a custom model to OpenSearch, you need to prepare it outside of your O
 
 As of OpenSearch 2.6, the ML Framework supports text-embedding models.
 
+As of OpenSearch 2.11, the ML framework supports sparse encoding models.
+
 ### Model format
 
 To use a model in OpenSearch, you'll need to export the model into a portable format. As of Version 2.5, OpenSearch only supports the [TorchScript](https://pytorch.org/docs/stable/jit.html) and [ONNX](https://onnx.ai/) formats.
 
 Furthermore, files must be saved as zip files before upload. Therefore, to ensure that ML Commons can upload your model, compress your TorchScript file before uploading. You can download an example file [here](https://github.com/opensearch-project/ml-commons/blob/2.x/ml-algorithms/src/test/resources/org/opensearch/ml/engine/algorithms/text_embedding/all-MiniLM-L6-v2_torchscript_sentence-transformer.zip).
 
+### Uploading your own model 
+
+For both text embedding and sparse encoding models, you must provide a tokenizer JSON file within the model zip file.
+
+For sparse encoding models, make sure your output format is `{"output":<sparse_vector>}` so that ML Commons can post-process the sparse vector.
+
+If you fine-tune a sparse model on your own dataset, you may also want to use your own sparse tokenizer model. It is preferable to provide your own [IDF](https://en.wikipedia.org/wiki/Tf%E2%80%93idf) JSON file in the tokenizer model zip file because this increases query performance when you use the tokenizer model in the query. Alternatively, you can use an OpenSearch-provided generic [IDF from MSMARCO](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-tokenizer-v1/1.0.0/torch_script/opensearch-neural-sparse-tokenizer-v1-1.0.0.zip). If the IDF file is not provided, the default weight of each token is set to 1, which may influence sparse neural search performance.  
 
 
 ### Model size

_ml-commons-plugin/pretrained-models.md

@@ -5,8 +5,9 @@ parent: Using custom models within OpenSearch
 nav_order: 120
 ---
 
-Pretrained models were taken out of experimental status and released to General Availability in OpenSearch 2.9.  
+Pretrained models are generally available in OpenSearch 2.9 and later. 
-{: .warning}
+Sparse encoding models are generally available in OpenSearch 2.11 and later. 
+{: .note}
 
 # Pretrained models
 
@@ -28,16 +29,37 @@ POST /_plugins/_ml/models/_upload
 }
 ```
 
+Note that for sparse encoding models, you still need to upload the full request body, as shown in the following example: 
+
+```
+POST /_plugins/_ml/models/_upload
+{
+    "name": "amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1",
+    "version": "1.0.0",
+    "description": "This is a neural sparse encoding model: It transfers text into sparse vector, and then extract nonzero index and value to entry and weights. It serves only in ingestion and customer should use tokenizer model in query.",
+    "model_format": "TORCH_SCRIPT",
+    "function_name": "SPARSE_ENCODING",
+    "model_content_hash_value": "9a41adb6c13cf49a7e3eff91aef62ed5035487a6eca99c996156d25be2800a9a",
+    "url":  "https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1/1.0.0/torch_script/opensearch-neural-sparse-encoding-doc-v1-1.0.0-torch_script.zip"
+}
+```
+{% include copy-curl.html %}
+
+You can find the `url` and `model_content_hash_value` in the model config link for each model. For more information, see the [Supported pretrained models section](#supported-pretrained-models). Set the `function_name` to `SPARSE_ENCODING` or `SPARSE_TOKENIZE`. 
+
+Note that the `function_name` parameter in the request corresponds to the `model_task_type` parameter in the model config. When using a pretrained model, make sure to change the name of the parameter from `model_task_type` to `function_name` in the model upload request.
+{: .important}
+
 For more information about how to upload and use ML models, see [Using custom models within OpenSearch]({{site.url}}{{site.baseurl}}/ml-commons-plugin/model-serving-framework/).
 
 ## Supported pretrained models
 
-The ML Framework supports the following models, categorized by type. All models are traced from [Hugging Face](https://huggingface.co/). Although models with the same type will have similar use cases, each model has a different model size and performs differently depending on your cluster. For a performance comparison of some pretrained models, see the [sbert documentation](https://www.sbert.net/docs/pretrained_models.html#model-overview).
+OpenSearch supports the following models, categorized by type. Text embedding models are sourced from [Hugging Face](https://huggingface.co/). Sparse encoding models are trained by OpenSearch. Although models with the same type will have similar use cases, each model has a different model size and will perform differently depending on your cluster setup. For a performance comparison of some pretrained models, see the [SBERT documentation](https://www.sbert.net/docs/pretrained_models.html#model-overview).
 
 
 ### Sentence transformers
 
-Sentence transformer models map sentences and paragraphs across a dimensional dense vector space. The number of vectors depends on the model. Use these models for use cases such as clustering and semantic search. 
+Sentence transformer models map sentences and paragraphs across a dimensional dense vector space. The number of vectors depends on the type of model. You can use these models for use cases such as clustering or semantic search.
 
 The following table provides a list of sentence transformer models and artifact links you can use to download them. Note that you must prefix the model name with `huggingface/`, as shown in the **Model name** column. As of OpenSearch 2.6, all artifacts are set to version 1.0.1.
 
@@ -51,4 +73,18 @@ The following table provides a list of sentence transformer models and artifact
 | `huggingface/sentence-transformers/multi-qa-MiniLM-L6-cos-v1` | 384-dimensional dense vector space. Designed for semantic search and trained on 215 million question/answer pairs. | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-MiniLM-L6-cos-v1/1.0.1/torch_script/sentence-transformers_multi-qa-MiniLM-L6-cos-v1-1.0.1-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-MiniLM-L6-cos-v1/1.0.1/torch_script/config.json) | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-MiniLM-L6-cos-v1/1.0.1/onnx/sentence-transformers_multi-qa-MiniLM-L6-cos-v1-1.0.1-onnx.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-MiniLM-L6-cos-v1/1.0.1/onnx/config.json) |
 | `huggingface/sentence-transformers/multi-qa-mpnet-base-dot-v1` | 384-dimensional dense vector space. | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-mpnet-base-dot-v1/1.0.1/torch_script/sentence-transformers_multi-qa-mpnet-base-dot-v1-1.0.1-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-mpnet-base-dot-v1/1.0.1/torch_script/config.json) | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-mpnet-base-dot-v1/1.0.1/onnx/sentence-transformers_multi-qa-mpnet-base-dot-v1-1.0.1-onnx.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/multi-qa-mpnet-base-dot-v1/1.0.1/onnx/config.json) |
 | `huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2` | 384-dimensional dense vector space. | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2/1.0.1/torch_script/sentence-transformers_paraphrase-MiniLM-L3-v2-1.0.1-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2/1.0.1/torch_script/config.json) | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2/1.0.1/onnx/sentence-transformers_paraphrase-MiniLM-L3-v2-1.0.1-onnx.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-MiniLM-L3-v2/1.0.1/onnx/config.json) |
-| `huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2` | 384-dimensional dense vector space. | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/torch_script/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2-1.0.1-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/torch_script/config.json) | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/onnx/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2-1.0.1-onnx.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/onnx/config.json) |
+| `huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2` | 384-dimensional dense vector space. | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/torch_script/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2-1.0.1-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/torch_script/config.json) | - [model_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/onnx/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2-1.0.1-onnx.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2/1.0.1/onnx/config.json) |
+
+
+### Sparse encoding models
+
+Sparse encoding models transfer text into a sparse vector and convert the vector to a list of `<token: weight>` pairs representing the text entry and its corresponding weight in the sparse vector. You can use these models for use cases such as clustering or sparse neural search.
+
+The following table provides a list of sparse encoding models and artifact links you can use to download them.
+
+| Model name | Auto-truncation | TorchScript artifact | 
+|---|---|
+| `amazon/neural-sparse/opensearch-neural-sparse-encoding-v1` | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-encoding-v1/1.0.0/torch_script/opensearch-neural-sparse-encoding-v1-1.0.0-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-encoding-v1/1.0.0/torch_script/config.json) | 
+| `amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1` | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1/1.0.0/torch_script/opensearch-neural-sparse-encoding-doc-v1-1.0.0-torch_script.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1/1.0.0/torch_script/config.json) | 
+| `amazon/neural-sparse/opensearch-neural-sparse-tokenizer-v1` | Yes | - [model_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-tokenizer-v1/1.0.0/torch_script/opensearch-neural-sparse-tokenizer-v1-1.0.0.zip)<br>- [config_url](https://artifacts.opensearch.org/models/ml-models/amazon/neural-sparse/opensearch-neural-sparse-tokenizer-v1/1.0.0/torch_script/config.json) | 
+

_search-plugins/neural-sparse-search.md

@@ -18,7 +18,7 @@ When selecting a model, choose one of the following options:
 - Use a sparse encoding model at ingestion time and a tokenizer model at search time (low performance, relatively low latency).
 
 **PREREQUISITE**<br>
-Before using sparse search, you must set up a sparse embedding model. For more information, see [Using custom models within OpenSearch]({{site.url}}{{site.baseurl}}/ml-commons-plugin/ml-framework/).
+Before using sparse search, make sure to set up a [pretrained sparse embedding model]({{site.url}}{{site.baseurl}}/ml-commons-plugin/pretrained-models/#sparse-encoding-models) or your own sparse embedding model. For more information, see [Using custom models within OpenSearch]({{site.url}}{{site.baseurl}}/ml-commons-plugin/ml-framework/).
 {: .note}
 
 ## Using sparse search