From e70d699ec68c3c756f3fad07935b3312c8523f11 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Tue, 23 Apr 2024 17:26:54 +0800
Subject: [PATCH 01/23] add fields and check

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml | 53 +++++++++++++++++++++++++---
 1 file changed, 48 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 68d75c90f..9c97d83da 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -8,6 +8,14 @@ on:
         required: true
         type: string
         default: "huggingface"
+      model_license:
+        description: "Model license (e.g. Apache-2.0)"
+        required: true
+        type: choice
+        default: "Apache-2.0"
+        options:
+          - "Apache-2.0"
+          - "MIT"
       model_id:
         description: "Model ID for auto-tracing and uploading (e.g. sentence-transformers/msmarco-distilbert-base-tas-b)"
         required: true
@@ -49,7 +57,18 @@ on:
         options:
         - "NO"
         - "YES"
-        
+      mit_copyright_statement:
+        description: "(Optional) Copyright statement for MIT licensed models. Should be picked from origin MIT license file. E.g. Copyright (c) {year} {author}"
+        required: false
+        type: string
+      mit_attribution_website:
+        description: "(Optional) The project website for MIT licensed models. The MIT license file is supposed to be found in this website"
+        required: false
+        type: string
+      mit_model_version:
+        description: "(Optional) The model version for MIT licensed models. Different from the model_version field above, this version should be quoted from the origin project website."
+        required: false
+        type: string
 
 jobs:
   # Step 2: Initiate workflow variable
@@ -73,6 +92,9 @@ jobs:
         embedding_dimension=${{ github.event.inputs.embedding_dimension }}
         pooling_mode=${{ github.event.inputs.pooling_mode }}
         model_description="${{ github.event.inputs.model_description }}"
+        mit_copyright_statement="${{ github.event.inputs.mit_copyright_statement }}"
+        mit_attribution_website="${{ github.event.inputs.mit_attribution_website }}"
+        mit_model_version="${{ github.event.inputs.mit_model_version }}"
         
         workflow_info="
         ============= Workflow Details ==============
@@ -83,11 +105,15 @@ jobs:
           
         ========= Workflow Input Information =========
         - Model ID: ${{ github.event.inputs.model_id }}
+        - Model License ${{ github.event.inputs.model_license }}
         - Model Version: ${{ github.event.inputs.model_version }}
         - Tracing Format: ${{ github.event.inputs.tracing_format }}
         - Embedding Dimension: ${embedding_dimension:-N/A}
         - Pooling Mode: ${pooling_mode:-N/A}
         - Model Description: ${model_description:-N/A}
+        - MIT Copyright Statement: ${mit_copyright_statement:-N/A}
+        - MIT Attribution Website: ${mit_attribution_website:-N/A}
+        - MIT Model Version: ${mit_model_version:-N/A}
         
         ======== Workflow Output Information =========
         - Embedding Verification: Passed"
@@ -96,16 +122,29 @@ jobs:
         echo "${workflow_info@E}" >> $GITHUB_OUTPUT
         echo "EOF" >> $GITHUB_OUTPUT
         echo "${workflow_info@E}"
+    - name: Check MIT license material
+      id: check_mit_license_material
+      run: |
+        if [[ "${{ github.event.inputs.model_license }}" == "MIT" ]]
+        then
+          echo "Uploading MIT licensed model"
+          if [[ "${{ github.event.inputs.mit_copyright_statement }}" == "" && "${{ github.event.inputs.mit_attribution_website }}" == "" && "${{ github.event.inputs.mit_model_version }}" == "" ]]
+          then
+              echo "missing materials for MIT model"
+              exit 1
+        fi
     - name: Initiate license_line
       id: init_license_line
       run: |
-        echo "verified=:white_check_mark: — It is verified that this model is licensed under Apache 2.0" >> $GITHUB_OUTPUT
-        echo "unverified=- [ ]  :warning: The license cannot be verified. Please confirm by yourself that the model is licensed under Apache 2.0  :warning:" >> $GITHUB_OUTPUT
+        echo "verified_apache=:white_check_mark: — It is verified that this model is licensed under Apache 2.0" >> $GITHUB_OUTPUT
+        echo "verified_mit=:white_check_mark: — It is verified that this model is licensed under MIT, and we have enough materials to generate the attribution file" >> $GITHUB_OUTPUT
+        echo "unverified=- [ ]  :warning: The license cannot be verified. Please confirm by yourself that the model is licensed under Apache 2.0 or MIT with enough materials  :warning:" >> $GITHUB_OUTPUT
     outputs:
       model_folder: ${{ steps.init_folders.outputs.model_folder }}
       sentence_transformer_folder: ${{ steps.init_folders.outputs.sentence_transformer_folder }}
       workflow_info: ${{ steps.init_workflow_info.outputs.workflow_info }}
-      verified_license_line: ${{ steps.init_license_line.outputs.verified }}
+      verified_apache_license_line: ${{ steps.init_license_line.outputs.verified_apache }}
+      verified_mit_license_line: ${{ steps.init_license_line.outputs.verified_mit }}
       unverified_license_line: ${{ steps.init_license_line.outputs.unverified }}
 
   # Step 3: Check if the model already exists in the model hub
@@ -175,11 +214,15 @@ jobs:
       - name: Export Arguments
         run: | 
           echo "MODEL_ID=${{ github.event.inputs.model_id }}" >> $GITHUB_ENV
+          echo "MODEL_LICENSE=${{ github.event.inputs.model_license }}" >> $GITHUB_ENV
           echo "MODEL_VERSION=${{ github.event.inputs.model_version }}" >> $GITHUB_ENV
           echo "TRACING_FORMAT=${{ github.event.inputs.tracing_format }}" >> $GITHUB_ENV
           echo "EMBEDDING_DIMENSION=${{ github.event.inputs.embedding_dimension }}" >> $GITHUB_ENV
           echo "POOLING_MODE=${{ github.event.inputs.pooling_mode }}" >> $GITHUB_ENV     
-          echo "MODEL_DESCRIPTION=${{ github.event.inputs.model_description }}" >> $GITHUB_ENV     
+          echo "MODEL_DESCRIPTION=${{ github.event.inputs.model_description }}" >> $GITHUB_ENV
+          echo "MIT_COPYRIGHT_STATEMENT=${{ github.event.inputs.mit_copyright_statement }}" >> $GITHUB_ENV
+          echo "MIT_ATTRIBUTION_WEBSITE=${{ github.event.inputs.mit_attribution_website }}" >> $GITHUB_ENV
+          echo "MIT_MODEL_VERSION=${{ github.event.inputs.mit_model_version }}" >> $GITHUB_ENV
       - name: Autotracing ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
         run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} trace"
       - name: Limit Model Size to 2GB

From dcea54e1b24effb1acd5085e2125fb47735404d2 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 09:39:06 +0000
Subject: [PATCH 02/23] add code for MIT licensed models

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .ci/run-repository.sh                         |  7 +-
 .github/workflows/model_uploader.yml          |  4 +-
 .../ml_models/sentencetransformermodel.py     | 34 ++++++-
 utils/model_uploader/model_autotracing.py     | 88 ++++++++++++++++---
 .../model_uploader/third_party_statements.py  | 60 +++++++++++++
 5 files changed, 176 insertions(+), 17 deletions(-)
 create mode 100644 utils/model_uploader/third_party_statements.py

diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
index bd97c17b6..08591c560 100755
--- a/.ci/run-repository.sh
+++ b/.ci/run-repository.sh
@@ -68,11 +68,15 @@ elif [[ "$TASK_TYPE" == "doc" ]]; then
 elif [[ "$TASK_TYPE" == "trace" ]]; then
   # Set up OpenSearch cluster & Run model autotracing (Invoked by model_uploader.yml workflow)
   echo -e "\033[34;1mINFO:\033[0m MODEL_ID: ${MODEL_ID}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MODEL_LICENSE: ${MODEL_LICENSE}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m MODEL_VERSION: ${MODEL_VERSION}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m TRACING_FORMAT: ${TRACING_FORMAT}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m EMBEDDING_DIMENSION: ${EMBEDDING_DIMENSION:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m POOLING_MODE: ${POOLING_MODE:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m MODEL_DESCRIPTION: ${MODEL_DESCRIPTION:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MIT_COPYRIGHT_STATEMENT: ${MIT_COPYRIGHT_STATEMENT:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MIT_ATTRIBUTION_WEBSITE: ${MIT_ATTRIBUTION_WEBSITE:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MIT_MODEL_VERSION: ${MIT_MODEL_VERSION:-N/A}\033[0m"
 
   docker run \
   --network=${network_name} \
@@ -84,7 +88,8 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   --env "TEST_TYPE=server" \
   --name opensearch-py-ml-trace-runner \
   opensearch-project/opensearch-py-ml \
-  nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"}
+  nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_LICENSE} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} \
+   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -mcs ${MIT_COPYRIGHT_STATEMENT} -maw ${MIT_ATTRIBUTION_WEBSITE} -mmv ${MIT_MODEL_VERSION}
   
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/
diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 9c97d83da..1c4a4746f 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -238,8 +238,8 @@ jobs:
       - name: License Verification
         id: license_verification
         run: |
-          apache_verified=$(<trace_output/apache_verified.txt)
-          if [[ $apache_verified == "True" ]]
+          license_verified=$(<trace_output/license_verified.txt)
+          if [[ $license_verified == "True" ]]
           then
             echo "license_line=${{ needs.init-workflow-var.outputs.verified_license_line }}" >> $GITHUB_OUTPUT
             echo "license_info=Automatically Verified" >> $GITHUB_OUTPUT
diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index 10f1174b5..9f4208de1 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -15,7 +15,7 @@
 import subprocess
 import time
 from pathlib import Path
-from typing import List
+from typing import List, Optional
 from zipfile import ZipFile
 
 import matplotlib.pyplot as plt
@@ -656,6 +656,20 @@ def _add_apache_license_to_model_zip_file(self, model_zip_file_path: str):
 
         with ZipFile(str(model_zip_file_path), "a") as zipObj:
             zipObj.writestr("LICENSE", r.content)
+            
+    def _add_third_party_statements_text_to_model_zip_file(self, third_party_statements_text: str, model_zip_file_path: str):
+        """
+        Add Statements text for non Apache-2.0 licensed third party model. Add it to the model zip file at model_zip_file_path
+
+        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_statements_text: string
+        :param model_zip_file_path: Path to the model zip file
+        :type model_zip_file_path: string
+        :return: no return value expected
+        :rtype: None
+        """
+        with ZipFile(str(model_zip_file_path), "a") as zipObj:
+            zipObj.writestr("THIRD-PARTY", third_party_statements_text)
 
     def zip_model(
         self,
@@ -771,6 +785,7 @@ def save_as_pt(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
+        third_party_statements_text: Optional[str] = None
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to torch script format,
@@ -802,10 +817,15 @@ def save_as_pt(
         :param add_apache_license:
             Optional, whether to add a Apache-2.0 license file to model zip file
         :type add_apache_license: string
+        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_statements_text: string
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
-
+        
+        if add_apache_license == True and not third_party_statements_text is None:
+            assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
+            
         model = SentenceTransformer(model_id)
 
         if model_name is None:
@@ -870,6 +890,8 @@ def save_as_pt(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
+        if not third_party_statements_text is None:
+            self._add_third_party_statements_text_to_model_zip_file(third_party_statements_text, zip_file_path)
 
         self.torch_script_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
@@ -883,6 +905,7 @@ def save_as_onnx(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
+        third_party_statements_text: Optional[str] = None
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to onnx format,
@@ -911,9 +934,14 @@ def save_as_onnx(
         :param add_apache_license:
             Optional, whether to add a Apache-2.0 license file to model zip file
         :type add_apache_license: string
+        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_statements_text: string
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
+        
+        if add_apache_license == True and not third_party_statements_text is None:
+            assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
 
         model = SentenceTransformer(model_id)
 
@@ -968,6 +996,8 @@ def save_as_onnx(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
+        if not third_party_statements_text is None:
+            self._add_third_party_statements_text_to_model_zip_file(third_party_statements_text, zip_file_path)
 
         self.onnx_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 3794087a8..6781cbe32 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -32,6 +32,7 @@
 from opensearch_py_ml.ml_commons import MLCommonClient
 from opensearch_py_ml.ml_models.sentencetransformermodel import SentenceTransformerModel
 from tests import OPENSEARCH_TEST_CLIENT
+from third_party_statements import generate_thirdpart_statements_for_MIT
 
 BOTH_FORMAT = "BOTH"
 TORCH_SCRIPT_FORMAT = "TORCH_SCRIPT"
@@ -43,7 +44,7 @@
 UPLOAD_FOLDER_PATH = "upload/"
 MODEL_CONFIG_FILE_NAME = "ml-commons_model_config.json"
 OUTPUT_DIR = "trace_output/"
-LICENSE_VAR_FILE = "apache_verified.txt"
+LICENSE_VAR_FILE = "license_verified.txt"
 DESCRIPTION_VAR_FILE = "description.txt"
 TEST_SENTENCES = [
     "First test sentence",
@@ -54,14 +55,14 @@
 ATOL_TEST = 1e-05
 
 
-def verify_license_in_md_file() -> bool:
+def verify_license_in_md_file(model_license: str = "Apache-2.0") -> bool:
     """
-    Verify that the model is licensed under Apache 2.0
+    Verify that the model is licensed under target model_license (Apache-2.0 or MIT)
     by looking at metadata in README.md file of the model
 
     TODO: Support other open source licenses in future
 
-    :return: Whether the model is licensed under Apache 2.0
+    :return: Whether the model is under target model_license
     :rtype: Bool
     """
     try:
@@ -75,21 +76,22 @@ def verify_license_in_md_file() -> bool:
     if start == -1 or end == -1:
         return False
     metadata_info = readme_data[start + 3 : end]
-    if "apache-2.0" in metadata_info.lower():
-        print("\nFound apache-2.0 license at " + TEMP_MODEL_PATH + "/README.md")
+    if model_license.lower() in metadata_info.lower():
+        print(f"\nFound {model_license} license at " + TEMP_MODEL_PATH + "/README.md")
         return True
     else:
-        print("\nDid not find apache-2.0 license at " + TEMP_MODEL_PATH + "/README.md")
+        print(f"\nDid not find {model_license} license at " + TEMP_MODEL_PATH + "/README.md")
         return False
 
-
 def trace_sentence_transformer_model(
     model_id: str,
+    model_license: str,
     model_version: str,
     model_format: str,
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
+    third_party_statements_text: Optional[str] = None
 ) -> Tuple[str, str]:
     """
     Trace the pretrained sentence transformer model, create a model config file,
@@ -97,6 +99,8 @@ def trace_sentence_transformer_model(
 
     :param model_id: Model ID of the pretrained model
     :type model_id: string
+    :param model_license: Model license ("Apache-2.0" or "MIT")
+    :type model_license: string
     :param model_version: Version of the pretrained model for registration
     :type model_version: string
     :param model_format: Model format ("TORCH_SCRIPT" or "ONNX")
@@ -107,6 +111,8 @@ def trace_sentence_transformer_model(
     :type pooling_mode: string
     :param model_description: Model description input
     :type model_description: string
+    :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+    :type third_party_statements_text: string
     :return: Tuple of model_path (path to model zip file) and model_config_path (path to model config json file)
     :rtype: Tuple[str, str]
     """
@@ -135,11 +141,14 @@ def trace_sentence_transformer_model(
             model_path = pre_trained_model.save_as_pt(
                 model_id=model_id,
                 sentences=TEST_SENTENCES,
-                add_apache_license=True,
+                add_apache_license=model_license=="Apache-2.0",
+                third_party_statements_text=third_party_statements_text
             )
         else:
             model_path = pre_trained_model.save_as_onnx(
-                model_id=model_id, add_apache_license=True
+                model_id=model_id,
+                add_apache_license=model_license=="Apache-2.0",
+                third_party_statements_text=third_party_statements_text
             )
     except Exception as e:
         assert False, f"Raised Exception during saving model as {model_format}: {e}"
@@ -407,17 +416,21 @@ def store_description_variable(config_path_for_checking_description: str) -> Non
 
 def main(
     model_id: str,
+    model_license: str,
     model_version: str,
     tracing_format: str,
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
+    third_party_statements_text: Optional[str] = None
 ) -> None:
     """
     Perform model auto-tracing and prepare files for uploading to OpenSearch model hub
 
     :param model_id: Model ID of the pretrained model
     :type model_id: string
+    :param model_license: Model license ("Apache-2.0" or "MIT")
+    :type model_license: string
     :param model_version: Version of the pretrained model for registration
     :type model_version: string
     :param tracing_format: Tracing format ("TORCH_SCRIPT", "ONNX", or "BOTH")
@@ -428,12 +441,15 @@ def main(
     :type pooling_mode: string
     :param model_description: Model description input
     :type model_description: string
+    :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+    :type third_party_statements_text: string
     :return: No return value expected
     :rtype: None
     """
 
     print("\n=== Begin running model_autotracing.py ===")
     print("Model ID: ", model_id)
+    print("Model License: ", model_license)
     print("Model Version: ", model_version)
     print("Tracing Format: ", tracing_format)
     print(
@@ -445,6 +461,10 @@ def main(
         "Model Description: ",
         model_description if model_description is not None else "N/A",
     )
+    print(
+        "Third Party Statements Text: ", 
+        third_party_statements_text if third_party_statements_text is not None else "N/A"
+    )
     print("==========================================")
 
     ml_client = MLCommonClient(OPENSEARCH_TEST_CLIENT)
@@ -455,7 +475,7 @@ def main(
     )
 
     pre_trained_model.save(path=TEMP_MODEL_PATH)
-    license_verified = verify_license_in_md_file()
+    license_verified = verify_license_in_md_file(model_license=model_license)
     try:
         shutil.rmtree(TEMP_MODEL_PATH)
     except Exception as e:
@@ -468,11 +488,13 @@ def main(
             torchscript_model_config_path,
         ) = trace_sentence_transformer_model(
             model_id,
+            model_license,
             model_version,
             TORCH_SCRIPT_FORMAT,
             embedding_dimension,
             pooling_mode,
             model_description,
+            third_party_statements_text
         )
 
         torchscript_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -509,11 +531,13 @@ def main(
             onnx_model_config_path,
         ) = trace_sentence_transformer_model(
             model_id,
+            model_license,
             model_version,
             ONNX_FORMAT,
             embedding_dimension,
             pooling_mode,
             model_description,
+            third_party_statements_text
         )
 
         onnx_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -557,6 +581,9 @@ def main(
         type=str,
         help="Model ID for auto-tracing and uploading (e.g. sentence-transformers/msmarco-distilbert-base-tas-b)",
     )
+    parser.add_argument(
+        "model_license", type=str, help="Model license (e.g. Apache-2.0)"
+    )
     parser.add_argument(
         "model_version", type=str, help="Model version number (e.g. 1.0.1)"
     )
@@ -593,13 +620,50 @@ def main(
         const=None,
         help="Model description if you want to overwrite the default description",
     )
+    parser.add_argument(
+        "-mcs",
+        "--mit_copyright_statement",
+        type=str,
+        nargs="?",
+        default=None,
+        const=None,
+        help="Copyright statement for MIT licensed models. Should be picked from origin MIT license file. E.g. Copyright (c) year author",
+    )
+    parser.add_argument(
+        "-maw",
+        "--mit_attribution_website",
+        type=str,
+        nargs="?",
+        default=None,
+        const=None,
+        help="The project website for MIT licensed models. The MIT license file is supposed to be found in this website",
+    )
+    parser.add_argument(
+        "-mmv",
+        "--mit_model_version",
+        type=str,
+        nargs="?",
+        default=None,
+        const=None,
+        help="The model version for MIT licensed models. Different from the model_version field above, this version should be quoted from the origin project website.",
+    )
+    
     args = parser.parse_args()
-
+    
+    if args.model_license == "MIT":
+        # in the model_uploader.yml we check that all materials are provided
+        third_party_statements_text = generate_thirdpart_statements_for_MIT(model_id=args.model_id, copyright_statement=args.mit_copyright_statement,
+                                            attribution_website=args.mit_attribution_website,model_version=args.model_version)
+    else:
+        third_party_statements_text = None
+        
     main(
         args.model_id,
+        args.model_license,
         args.model_version,
         args.tracing_format,
         args.embedding_dimension,
         args.pooling_mode,
         args.model_description,
+        third_party_statements_text
     )
diff --git a/utils/model_uploader/third_party_statements.py b/utils/model_uploader/third_party_statements.py
new file mode 100644
index 000000000..6c24640b1
--- /dev/null
+++ b/utils/model_uploader/third_party_statements.py
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: Apache-2.0
+# The OpenSearch Contributors require contributions made to
+# this file be licensed under the Apache-2.0 license or a
+# compatible open source license.
+# Any modifications Copyright OpenSearch Contributors. See
+# GitHub history for details.
+from string import Template
+
+MIT_TEMPLATE = Template("""
+** $model_id; version $model_version $attribution_website
+$copyright_statement
+ 
+MIT License
+
+$copyright_statement
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+""")
+
+def generate_thirdpart_statements_for_MIT(
+    model_id: str,
+    copyright_statement: str, 
+    attribution_website: str, 
+    model_version:str
+) -> str:
+    """
+    Generate statements text for MIT-licensed third party model. The result should be put in the final artifact.
+    
+    :param model_id: Model ID of the pretrained model
+    :type model_id: string
+    :param copyright_statement: MIT models copyright statement
+    :type copyright_statement: string
+    :param attribution_website: The project website for MIT licensed models
+    :type attribution_website: string
+    :param model_version: The model version for MIT licensed models
+    :type model_version: string
+    :return: Statements text for MIT-licensed third party model.
+    :rtype: str
+    """
+    
+    
+    result = MIT_TEMPLATE.substitute(model_id=model_id, copyright_statement=copyright_statement,
+                                     attribution_website=attribution_website, model_version=model_version)
+    return result.strip()
\ No newline at end of file

From 607336cedea6e9ad73ea056f4eb2f69dacad2272 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 09:53:54 +0000
Subject: [PATCH 03/23] license line; remove manual approve

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 1c4a4746f..d80d0d868 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -241,7 +241,12 @@ jobs:
           license_verified=$(<trace_output/license_verified.txt)
           if [[ $license_verified == "True" ]]
           then
-            echo "license_line=${{ needs.init-workflow-var.outputs.verified_license_line }}" >> $GITHUB_OUTPUT
+            if [[ "${{ github.event.inputs.model_license }}" == "Apache-2.0" ]]
+            then
+              echo "license_line=${{ needs.init-workflow-var.outputs.verified_apache_license_line }}" >> $GITHUB_OUTPUT
+            else
+              echo "license_line=${{ needs.init-workflow-var.outputs.verified_mit_license_line }}" >> $GITHUB_OUTPUT
+            fi
             echo "license_info=Automatically Verified" >> $GITHUB_OUTPUT
           else
             echo "license_line=${{ needs.init-workflow-var.outputs.unverified_license_line }}" >> $GITHUB_OUTPUT 
@@ -312,14 +317,14 @@ jobs:
           echo "${issue_body@E}" >> $GITHUB_OUTPUT
           echo "EOF" >> $GITHUB_OUTPUT
           echo "${issue_body@E}"
-      - uses: trstringer/manual-approval@v1
-        with:
-          secret: ${{ github.TOKEN }}
-          approvers: ${{ steps.get_approvers.outputs.approvers }}
-          minimum-approvals: 2
-          issue-title: "Upload Model to OpenSearch Model Hub (${{ github.event.inputs.model_id }})"
-          issue-body: ${{ steps.create_issue_body.outputs.issue_body }}
-          exclude-workflow-initiator-as-approver: false
+      # - uses: trstringer/manual-approval@v1
+      #   with:
+      #     secret: ${{ github.TOKEN }}
+      #     approvers: ${{ steps.get_approvers.outputs.approvers }}
+      #     minimum-approvals: 2
+      #     issue-title: "Upload Model to OpenSearch Model Hub (${{ github.event.inputs.model_id }})"
+      #     issue-body: ${{ steps.create_issue_body.outputs.issue_body }}
+      #     exclude-workflow-initiator-as-approver: false
       
   # Step 6: Download the artifacts & Upload it to the S3 bucket
   model-uploading:

From 7adfbf354b5d4bc7504dbf9327fc236952d739eb Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 10:02:59 +0000
Subject: [PATCH 04/23] rename to third_party_statements_text

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .../ml_models/sentencetransformermodel.py     | 32 +++++++++----------
 utils/model_uploader/model_autotracing.py     | 28 ++++++++--------
 2 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index 9f4208de1..3934190ae 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -657,19 +657,19 @@ def _add_apache_license_to_model_zip_file(self, model_zip_file_path: str):
         with ZipFile(str(model_zip_file_path), "a") as zipObj:
             zipObj.writestr("LICENSE", r.content)
             
-    def _add_third_party_statements_text_to_model_zip_file(self, third_party_statements_text: str, model_zip_file_path: str):
+    def _add_third_party_copyrights_statements_to_model_zip_file(self, third_party_copyrights_statements: str, model_zip_file_path: str):
         """
         Add Statements text for non Apache-2.0 licensed third party model. Add it to the model zip file at model_zip_file_path
 
-        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
-        :type third_party_statements_text: string
+        :param third_party_copyrights_statements: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_copyrights_statements: string
         :param model_zip_file_path: Path to the model zip file
         :type model_zip_file_path: string
         :return: no return value expected
         :rtype: None
         """
         with ZipFile(str(model_zip_file_path), "a") as zipObj:
-            zipObj.writestr("THIRD-PARTY", third_party_statements_text)
+            zipObj.writestr("THIRD-PARTY", third_party_copyrights_statements)
 
     def zip_model(
         self,
@@ -785,7 +785,7 @@ def save_as_pt(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
-        third_party_statements_text: Optional[str] = None
+        third_party_copyrights_statements: Optional[str] = None
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to torch script format,
@@ -817,13 +817,13 @@ def save_as_pt(
         :param add_apache_license:
             Optional, whether to add a Apache-2.0 license file to model zip file
         :type add_apache_license: string
-        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
-        :type third_party_statements_text: string
+        :param third_party_copyrights_statements: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_copyrights_statements: string
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
         
-        if add_apache_license == True and not third_party_statements_text is None:
+        if add_apache_license == True and not third_party_copyrights_statements is None:
             assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
             
         model = SentenceTransformer(model_id)
@@ -890,8 +890,8 @@ def save_as_pt(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
-        if not third_party_statements_text is None:
-            self._add_third_party_statements_text_to_model_zip_file(third_party_statements_text, zip_file_path)
+        if not third_party_copyrights_statements is None:
+            self._add_third_party_copyrights_statements_to_model_zip_file(third_party_copyrights_statements, zip_file_path)
 
         self.torch_script_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
@@ -905,7 +905,7 @@ def save_as_onnx(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
-        third_party_statements_text: Optional[str] = None
+        third_party_copyrights_statements: Optional[str] = None
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to onnx format,
@@ -934,13 +934,13 @@ def save_as_onnx(
         :param add_apache_license:
             Optional, whether to add a Apache-2.0 license file to model zip file
         :type add_apache_license: string
-        :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
-        :type third_party_statements_text: string
+        :param third_party_copyrights_statements: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+        :type third_party_copyrights_statements: string
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
         
-        if add_apache_license == True and not third_party_statements_text is None:
+        if add_apache_license == True and not third_party_copyrights_statements is None:
             assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
 
         model = SentenceTransformer(model_id)
@@ -996,8 +996,8 @@ def save_as_onnx(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
-        if not third_party_statements_text is None:
-            self._add_third_party_statements_text_to_model_zip_file(third_party_statements_text, zip_file_path)
+        if not third_party_copyrights_statements is None:
+            self._add_third_party_copyrights_statements_to_model_zip_file(third_party_copyrights_statements, zip_file_path)
 
         self.onnx_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 6781cbe32..517308792 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -91,7 +91,7 @@ def trace_sentence_transformer_model(
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
-    third_party_statements_text: Optional[str] = None
+    third_party_copyrights_statements: Optional[str] = None
 ) -> Tuple[str, str]:
     """
     Trace the pretrained sentence transformer model, create a model config file,
@@ -111,8 +111,8 @@ def trace_sentence_transformer_model(
     :type pooling_mode: string
     :param model_description: Model description input
     :type model_description: string
-    :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
-    :type third_party_statements_text: string
+    :param third_party_copyrights_statements: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+    :type third_party_copyrights_statements: string
     :return: Tuple of model_path (path to model zip file) and model_config_path (path to model config json file)
     :rtype: Tuple[str, str]
     """
@@ -142,13 +142,13 @@ def trace_sentence_transformer_model(
                 model_id=model_id,
                 sentences=TEST_SENTENCES,
                 add_apache_license=model_license=="Apache-2.0",
-                third_party_statements_text=third_party_statements_text
+                third_party_copyrights_statements=third_party_copyrights_statements
             )
         else:
             model_path = pre_trained_model.save_as_onnx(
                 model_id=model_id,
                 add_apache_license=model_license=="Apache-2.0",
-                third_party_statements_text=third_party_statements_text
+                third_party_copyrights_statements=third_party_copyrights_statements
             )
     except Exception as e:
         assert False, f"Raised Exception during saving model as {model_format}: {e}"
@@ -422,7 +422,7 @@ def main(
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
-    third_party_statements_text: Optional[str] = None
+    third_party_copyrights_statements: Optional[str] = None
 ) -> None:
     """
     Perform model auto-tracing and prepare files for uploading to OpenSearch model hub
@@ -441,8 +441,8 @@ def main(
     :type pooling_mode: string
     :param model_description: Model description input
     :type model_description: string
-    :param third_party_statements_text: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
-    :type third_party_statements_text: string
+    :param third_party_copyrights_statements: Statements text for non Apache-2.0 licensed third party model. Should be put in the final artifact.
+    :type third_party_copyrights_statements: string
     :return: No return value expected
     :rtype: None
     """
@@ -463,7 +463,7 @@ def main(
     )
     print(
         "Third Party Statements Text: ", 
-        third_party_statements_text if third_party_statements_text is not None else "N/A"
+        third_party_copyrights_statements if third_party_copyrights_statements is not None else "N/A"
     )
     print("==========================================")
 
@@ -494,7 +494,7 @@ def main(
             embedding_dimension,
             pooling_mode,
             model_description,
-            third_party_statements_text
+            third_party_copyrights_statements
         )
 
         torchscript_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -537,7 +537,7 @@ def main(
             embedding_dimension,
             pooling_mode,
             model_description,
-            third_party_statements_text
+            third_party_copyrights_statements
         )
 
         onnx_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -652,10 +652,10 @@ def main(
     
     if args.model_license == "MIT":
         # in the model_uploader.yml we check that all materials are provided
-        third_party_statements_text = generate_thirdpart_statements_for_MIT(model_id=args.model_id, copyright_statement=args.mit_copyright_statement,
+        third_party_copyrights_statements = generate_thirdpart_statements_for_MIT(model_id=args.model_id, copyright_statement=args.mit_copyright_statement,
                                             attribution_website=args.mit_attribution_website,model_version=args.model_version)
     else:
-        third_party_statements_text = None
+        third_party_copyrights_statements = None
         
     main(
         args.model_id,
@@ -665,5 +665,5 @@ def main(
         args.embedding_dimension,
         args.pooling_mode,
         args.model_description,
-        third_party_statements_text
+        third_party_copyrights_statements
     )

From 7d183788a49cf028eb24cbbfd667e160166e39e2 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 10:13:01 +0000
Subject: [PATCH 05/23] change to copyright statements

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml      | 34 +++++++----------------
 utils/model_uploader/model_autotracing.py | 33 +++-------------------
 2 files changed, 14 insertions(+), 53 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index d80d0d868..d0fe97dc2 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -57,16 +57,8 @@ on:
         options:
         - "NO"
         - "YES"
-      mit_copyright_statement:
-        description: "(Optional) Copyright statement for MIT licensed models. Should be picked from origin MIT license file. E.g. Copyright (c) {year} {author}"
-        required: false
-        type: string
-      mit_attribution_website:
-        description: "(Optional) The project website for MIT licensed models. The MIT license file is supposed to be found in this website"
-        required: false
-        type: string
-      mit_model_version:
-        description: "(Optional) The model version for MIT licensed models. Different from the model_version field above, this version should be quoted from the origin project website."
+      third_party_copyrights_statements:
+        description: "(Optional) Copyright statements for MIT licensed models. Should be put in the final artifact."
         required: false
         type: string
 
@@ -92,9 +84,7 @@ jobs:
         embedding_dimension=${{ github.event.inputs.embedding_dimension }}
         pooling_mode=${{ github.event.inputs.pooling_mode }}
         model_description="${{ github.event.inputs.model_description }}"
-        mit_copyright_statement="${{ github.event.inputs.mit_copyright_statement }}"
-        mit_attribution_website="${{ github.event.inputs.mit_attribution_website }}"
-        mit_model_version="${{ github.event.inputs.mit_model_version }}"
+        third_party_copyrights_statements="${{ github.event.inputs.third_party_copyrights_statements }}"
         
         workflow_info="
         ============= Workflow Details ==============
@@ -111,9 +101,7 @@ jobs:
         - Embedding Dimension: ${embedding_dimension:-N/A}
         - Pooling Mode: ${pooling_mode:-N/A}
         - Model Description: ${model_description:-N/A}
-        - MIT Copyright Statement: ${mit_copyright_statement:-N/A}
-        - MIT Attribution Website: ${mit_attribution_website:-N/A}
-        - MIT Model Version: ${mit_model_version:-N/A}
+        - Third Party Copyrights Statements: ${third_party_copyrights_statements:-N/A}
         
         ======== Workflow Output Information =========
         - Embedding Verification: Passed"
@@ -122,22 +110,22 @@ jobs:
         echo "${workflow_info@E}" >> $GITHUB_OUTPUT
         echo "EOF" >> $GITHUB_OUTPUT
         echo "${workflow_info@E}"
-    - name: Check MIT license material
-      id: check_mit_license_material
+    - name: Check MIT license copyright statements
+      id: check_mit_license_copyright_statements
       run: |
         if [[ "${{ github.event.inputs.model_license }}" == "MIT" ]]
         then
           echo "Uploading MIT licensed model"
-          if [[ "${{ github.event.inputs.mit_copyright_statement }}" == "" && "${{ github.event.inputs.mit_attribution_website }}" == "" && "${{ github.event.inputs.mit_model_version }}" == "" ]]
+          if [[ "${{ github.event.inputs.third_party_copyrights_statements }}" == "" ]]
           then
-              echo "missing materials for MIT model"
+              echo "missing copyright statements for MIT model"
               exit 1
         fi
     - name: Initiate license_line
       id: init_license_line
       run: |
         echo "verified_apache=:white_check_mark: — It is verified that this model is licensed under Apache 2.0" >> $GITHUB_OUTPUT
-        echo "verified_mit=:white_check_mark: — It is verified that this model is licensed under MIT, and we have enough materials to generate the attribution file" >> $GITHUB_OUTPUT
+        echo "verified_mit=:white_check_mark: — It is verified that this model is licensed under MIT, and we have provided copyright statements" >> $GITHUB_OUTPUT
         echo "unverified=- [ ]  :warning: The license cannot be verified. Please confirm by yourself that the model is licensed under Apache 2.0 or MIT with enough materials  :warning:" >> $GITHUB_OUTPUT
     outputs:
       model_folder: ${{ steps.init_folders.outputs.model_folder }}
@@ -220,9 +208,7 @@ jobs:
           echo "EMBEDDING_DIMENSION=${{ github.event.inputs.embedding_dimension }}" >> $GITHUB_ENV
           echo "POOLING_MODE=${{ github.event.inputs.pooling_mode }}" >> $GITHUB_ENV     
           echo "MODEL_DESCRIPTION=${{ github.event.inputs.model_description }}" >> $GITHUB_ENV
-          echo "MIT_COPYRIGHT_STATEMENT=${{ github.event.inputs.mit_copyright_statement }}" >> $GITHUB_ENV
-          echo "MIT_ATTRIBUTION_WEBSITE=${{ github.event.inputs.mit_attribution_website }}" >> $GITHUB_ENV
-          echo "MIT_MODEL_VERSION=${{ github.event.inputs.mit_model_version }}" >> $GITHUB_ENV
+          echo "THIRD_PARTY_COPYRIGHTS_STATEMENTS=${{ github.event.inputs.third_party_copyrights_statements }}" >> $GITHUB_ENV
       - name: Autotracing ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
         run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} trace"
       - name: Limit Model Size to 2GB
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 517308792..4fa9545df 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -621,41 +621,16 @@ def main(
         help="Model description if you want to overwrite the default description",
     )
     parser.add_argument(
-        "-mcs",
-        "--mit_copyright_statement",
+        "-tpcs",
+        "--third_party_copyrights_statements",
         type=str,
         nargs="?",
         default=None,
         const=None,
-        help="Copyright statement for MIT licensed models. Should be picked from origin MIT license file. E.g. Copyright (c) year author",
-    )
-    parser.add_argument(
-        "-maw",
-        "--mit_attribution_website",
-        type=str,
-        nargs="?",
-        default=None,
-        const=None,
-        help="The project website for MIT licensed models. The MIT license file is supposed to be found in this website",
-    )
-    parser.add_argument(
-        "-mmv",
-        "--mit_model_version",
-        type=str,
-        nargs="?",
-        default=None,
-        const=None,
-        help="The model version for MIT licensed models. Different from the model_version field above, this version should be quoted from the origin project website.",
+        help="Copyright statement for MIT licensed models.",
     )
     
     args = parser.parse_args()
-    
-    if args.model_license == "MIT":
-        # in the model_uploader.yml we check that all materials are provided
-        third_party_copyrights_statements = generate_thirdpart_statements_for_MIT(model_id=args.model_id, copyright_statement=args.mit_copyright_statement,
-                                            attribution_website=args.mit_attribution_website,model_version=args.model_version)
-    else:
-        third_party_copyrights_statements = None
         
     main(
         args.model_id,
@@ -665,5 +640,5 @@ def main(
         args.embedding_dimension,
         args.pooling_mode,
         args.model_description,
-        third_party_copyrights_statements
+        args.third_party_copyrights_statements
     )

From a5c6627ef74dedd6035dff2b0d6e7e6a2b3cd2cd Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 10:15:41 +0000
Subject: [PATCH 06/23] change to copyright statements

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .ci/run-repository.sh | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
index 08591c560..67e156029 100755
--- a/.ci/run-repository.sh
+++ b/.ci/run-repository.sh
@@ -74,9 +74,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   echo -e "\033[34;1mINFO:\033[0m EMBEDDING_DIMENSION: ${EMBEDDING_DIMENSION:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m POOLING_MODE: ${POOLING_MODE:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m MODEL_DESCRIPTION: ${MODEL_DESCRIPTION:-N/A}\033[0m"
-  echo -e "\033[34;1mINFO:\033[0m MIT_COPYRIGHT_STATEMENT: ${MIT_COPYRIGHT_STATEMENT:-N/A}\033[0m"
-  echo -e "\033[34;1mINFO:\033[0m MIT_ATTRIBUTION_WEBSITE: ${MIT_ATTRIBUTION_WEBSITE:-N/A}\033[0m"
-  echo -e "\033[34;1mINFO:\033[0m MIT_MODEL_VERSION: ${MIT_MODEL_VERSION:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m THIRD_PARTY_COPYRIGHTS_STATEMENTS: ${THIRD_PARTY_COPYRIGHTS_STATEMENTS:-N/A}\033[0m"
 
   docker run \
   --network=${network_name} \
@@ -89,7 +87,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   --name opensearch-py-ml-trace-runner \
   opensearch-project/opensearch-py-ml \
   nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_LICENSE} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} \
-   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -mcs ${MIT_COPYRIGHT_STATEMENT} -maw ${MIT_ATTRIBUTION_WEBSITE} -mmv ${MIT_MODEL_VERSION}
+   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -tpcs ${THIRD_PARTY_COPYRIGHTS_STATEMENTS}
   
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/

From 46b99d74173a2a496a7478af6bab656327f0ca32 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Wed, 24 Apr 2024 10:24:01 +0000
Subject: [PATCH 07/23] add fi

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index d0fe97dc2..fc9addad6 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -120,6 +120,7 @@ jobs:
           then
               echo "missing copyright statements for MIT model"
               exit 1
+          fi
         fi
     - name: Initiate license_line
       id: init_license_line

From efbc53389f7662a47f470443f9303e43db9fc3ab Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 03:06:25 +0000
Subject: [PATCH 08/23] add quote to string var

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .ci/run-repository.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
index 67e156029..8754f9dd8 100755
--- a/.ci/run-repository.sh
+++ b/.ci/run-repository.sh
@@ -87,7 +87,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   --name opensearch-py-ml-trace-runner \
   opensearch-project/opensearch-py-ml \
   nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_LICENSE} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} \
-   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -tpcs ${THIRD_PARTY_COPYRIGHTS_STATEMENTS}
+   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -tpcs "${THIRD_PARTY_COPYRIGHTS_STATEMENTS}"
   
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/

From 3e9871dc2a093ea56a21c52053d2784f432d713f Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 06:26:52 +0000
Subject: [PATCH 09/23] fix quote

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index fc9addad6..7b2f6f6fa 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -290,7 +290,7 @@ jobs:
       - name: Create Issue Body
         id: create_issue_body
         run: |    
-          issue_body="Please approve or deny opensearch-py-ml model uploading:
+          issue_body='Please approve or deny opensearch-py-ml model uploading:
           
           ${{ needs.model-auto-tracing.outputs.license_line }}
           
@@ -298,7 +298,7 @@ jobs:
           ${{ needs.model-auto-tracing.outputs.model_description_info }}
           
           ===== Dry Run of Model Uploading =====
-          ${{ needs.model-auto-tracing.outputs.dryrun_output }}"
+          ${{ needs.model-auto-tracing.outputs.dryrun_output }}'
 
           echo "issue_body<<EOF" >> $GITHUB_OUTPUT
           echo "${issue_body@E}" >> $GITHUB_OUTPUT

From 20d4fc851d00bd06ad31affb3848e8d52b0bfc3e Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 06:39:14 +0000
Subject: [PATCH 10/23] fix quote

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 7b2f6f6fa..21437e628 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -375,14 +375,14 @@ jobs:
       - name: Create PR Body
         id: create_pr_body
         run: |
-          pr_body="
+          pr_body='
           - [ ] This PR made commit to only these three files: MODEL_UPLOAD_HISTORY.md, supported_models.json, and CHANGELOG.md.
           - [ ] CHANGELOG.md has been updated by the workflow or by you if the workflow fails to do so. 
           - [ ] Merge conflicts have been resolved.
           
           ${{ needs.init-workflow-var.outputs.workflow_info }}
           ${{ needs.model-auto-tracing.outputs.license_info }}
-          ${{ needs.model-auto-tracing.outputs.model_description_info }}"
+          ${{ needs.model-auto-tracing.outputs.model_description_info }}'
           
           echo "pr_body<<EOF" >> $GITHUB_OUTPUT
           echo "${pr_body@E}" >> $GITHUB_OUTPUT

From 337ffa984652ebb9f5b2e0e2c34ba10ee63a208c Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 07:17:40 +0000
Subject: [PATCH 11/23] log failure state

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 opensearch_py_ml/ml_commons/ml_commons_client.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/opensearch_py_ml/ml_commons/ml_commons_client.py b/opensearch_py_ml/ml_commons/ml_commons_client.py
index 2f387ad11..cc6676ebe 100644
--- a/opensearch_py_ml/ml_commons/ml_commons_client.py
+++ b/opensearch_py_ml/ml_commons/ml_commons_client.py
@@ -382,7 +382,7 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             elif model_state == "PARTIALLY_DEPLOYED":
                 print("Model deployed only partially")
             else:
-                raise Exception("Model deployment failed")
+                raise Exception("Model deployment failed, model_state:",model_state)
 
         return self._get_task_info(task_id)
 

From a0073019c35095c3ed14eab5c0ecd81d70d448f4 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 08:15:19 +0000
Subject: [PATCH 12/23] use url

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .ci/run-repository.sh                         |  4 +-
 .github/workflows/model_uploader.yml          | 23 ++++---
 opensearch_py_ml/field_mappings.py            |  6 +-
 .../ml_commons/ml_commons_client.py           |  2 +-
 opensearch_py_ml/ml_commons/model_uploader.py |  6 +-
 .../metrics_correlation/event_detection.py    |  6 +-
 .../ml_models/sentencetransformermodel.py     | 38 +++++++----
 utils/model_uploader/model_autotracing.py     | 55 +++++++++-------
 .../model_uploader/third_party_statements.py  | 66 ++++++-------------
 9 files changed, 103 insertions(+), 103 deletions(-)

diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
index 8754f9dd8..b3b6974eb 100755
--- a/.ci/run-repository.sh
+++ b/.ci/run-repository.sh
@@ -74,7 +74,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   echo -e "\033[34;1mINFO:\033[0m EMBEDDING_DIMENSION: ${EMBEDDING_DIMENSION:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m POOLING_MODE: ${POOLING_MODE:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m MODEL_DESCRIPTION: ${MODEL_DESCRIPTION:-N/A}\033[0m"
-  echo -e "\033[34;1mINFO:\033[0m THIRD_PARTY_COPYRIGHTS_STATEMENTS: ${THIRD_PARTY_COPYRIGHTS_STATEMENTS:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m MIT_LICENSE_URL: ${MIT_LICENSE_URL:-N/A}\033[0m"
 
   docker run \
   --network=${network_name} \
@@ -87,7 +87,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   --name opensearch-py-ml-trace-runner \
   opensearch-project/opensearch-py-ml \
   nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_LICENSE} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} \
-   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -tpcs "${THIRD_PARTY_COPYRIGHTS_STATEMENTS}"
+   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -mlu ${MIT_LICENSE_URL}
   
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/
diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 21437e628..39d6353f0 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -57,8 +57,8 @@ on:
         options:
         - "NO"
         - "YES"
-      third_party_copyrights_statements:
-        description: "(Optional) Copyright statements for MIT licensed models. Should be put in the final artifact."
+      MIT_license_url:
+        description: "(Optional) MIT license of the huggingface MIT model."
         required: false
         type: string
 
@@ -84,7 +84,7 @@ jobs:
         embedding_dimension=${{ github.event.inputs.embedding_dimension }}
         pooling_mode=${{ github.event.inputs.pooling_mode }}
         model_description="${{ github.event.inputs.model_description }}"
-        third_party_copyrights_statements="${{ github.event.inputs.third_party_copyrights_statements }}"
+        MIT_license_url="${{ github.event.inputs.MIT_license_url }}"
         
         workflow_info="
         ============= Workflow Details ==============
@@ -101,7 +101,7 @@ jobs:
         - Embedding Dimension: ${embedding_dimension:-N/A}
         - Pooling Mode: ${pooling_mode:-N/A}
         - Model Description: ${model_description:-N/A}
-        - Third Party Copyrights Statements: ${third_party_copyrights_statements:-N/A}
+        - MIT License Url: ${MIT_license_url:-N/A}
         
         ======== Workflow Output Information =========
         - Embedding Verification: Passed"
@@ -110,15 +110,20 @@ jobs:
         echo "${workflow_info@E}" >> $GITHUB_OUTPUT
         echo "EOF" >> $GITHUB_OUTPUT
         echo "${workflow_info@E}"
-    - name: Check MIT license copyright statements
-      id: check_mit_license_copyright_statements
+    - name: Check MIT license url
+      id: check_mit_license_url
       run: |
         if [[ "${{ github.event.inputs.model_license }}" == "MIT" ]]
         then
           echo "Uploading MIT licensed model"
-          if [[ "${{ github.event.inputs.third_party_copyrights_statements }}" == "" ]]
+          if [[ "${{ github.event.inputs.MIT_license_url }}" == "" ]]
           then
-              echo "missing copyright statements for MIT model"
+              echo "missing MIT license url"
+              exit 1
+          fi
+          if [[ "${{ github.event.inputs.model_source }}" == "" ]]
+          then
+              echo "only support MIT models from huggingface now"
               exit 1
           fi
         fi
@@ -209,7 +214,7 @@ jobs:
           echo "EMBEDDING_DIMENSION=${{ github.event.inputs.embedding_dimension }}" >> $GITHUB_ENV
           echo "POOLING_MODE=${{ github.event.inputs.pooling_mode }}" >> $GITHUB_ENV     
           echo "MODEL_DESCRIPTION=${{ github.event.inputs.model_description }}" >> $GITHUB_ENV
-          echo "THIRD_PARTY_COPYRIGHTS_STATEMENTS=${{ github.event.inputs.third_party_copyrights_statements }}" >> $GITHUB_ENV
+          echo "MIT_LICENSE_URL=${{ github.event.inputs.MIT_license_url }}" >> $GITHUB_ENV
       - name: Autotracing ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
         run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} trace"
       - name: Limit Model Size to 2GB
diff --git a/opensearch_py_ml/field_mappings.py b/opensearch_py_ml/field_mappings.py
index 75bbd1833..b3c83914a 100644
--- a/opensearch_py_ml/field_mappings.py
+++ b/opensearch_py_ml/field_mappings.py
@@ -445,9 +445,9 @@ def find_aggregatable(row, df):
                 try:
                     series = df.loc[df.os_field_name == os_field_name_keyword]
                     if not series.empty and series.is_aggregatable.squeeze():
-                        row_as_dict["aggregatable_os_field_name"] = (
-                            os_field_name_keyword
-                        )
+                        row_as_dict[
+                            "aggregatable_os_field_name"
+                        ] = os_field_name_keyword
                     else:
                         row_as_dict["aggregatable_os_field_name"] = None
                 except KeyError:
diff --git a/opensearch_py_ml/ml_commons/ml_commons_client.py b/opensearch_py_ml/ml_commons/ml_commons_client.py
index cc6676ebe..8b50a95cc 100644
--- a/opensearch_py_ml/ml_commons/ml_commons_client.py
+++ b/opensearch_py_ml/ml_commons/ml_commons_client.py
@@ -382,7 +382,7 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             elif model_state == "PARTIALLY_DEPLOYED":
                 print("Model deployed only partially")
             else:
-                raise Exception("Model deployment failed, model_state:",model_state)
+                raise Exception("Model deployment failed, model_state:", model_state)
 
         return self._get_task_info(task_id)
 
diff --git a/opensearch_py_ml/ml_commons/model_uploader.py b/opensearch_py_ml/ml_commons/model_uploader.py
index 850f6a80a..af7af2f62 100644
--- a/opensearch_py_ml/ml_commons/model_uploader.py
+++ b/opensearch_py_ml/ml_commons/model_uploader.py
@@ -95,9 +95,9 @@ def _register_model(
         model_meta_json[TOTAL_CHUNKS_FIELD] = total_num_chunks
 
         if MODEL_CONTENT_SIZE_IN_BYTES_FIELD not in model_meta_json:
-            model_meta_json[MODEL_CONTENT_SIZE_IN_BYTES_FIELD] = (
-                model_content_size_in_bytes
-            )
+            model_meta_json[
+                MODEL_CONTENT_SIZE_IN_BYTES_FIELD
+            ] = model_content_size_in_bytes
         if MODEL_CONTENT_HASH_VALUE not in model_meta_json:
             # Generate the sha1 hash for the model zip file
             hash_val_model_file = _generate_model_content_hash_value(model_path)
diff --git a/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py b/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
index f6e5187cd..f9395d1a4 100644
--- a/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
+++ b/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
@@ -94,9 +94,9 @@ def merge_events(
     send = ends[ix]
     sevents = candidates[ix, :]
 
-    merged: List[Dict[str, torch.Tensor]] = (
-        []
-    )  # merge in linear pass over time dimension
+    merged: List[
+        Dict[str, torch.Tensor]
+    ] = []  # merge in linear pass over time dimension
     currstart = torch.tensor([-1])
     currend = torch.tensor([-1])
     currevent = torch.ones(T) * -1.0
diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index 3934190ae..63e3e6e56 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -656,8 +656,10 @@ def _add_apache_license_to_model_zip_file(self, model_zip_file_path: str):
 
         with ZipFile(str(model_zip_file_path), "a") as zipObj:
             zipObj.writestr("LICENSE", r.content)
-            
-    def _add_third_party_copyrights_statements_to_model_zip_file(self, third_party_copyrights_statements: str, model_zip_file_path: str):
+
+    def _add_third_party_copyrights_statements_to_model_zip_file(
+        self, third_party_copyrights_statements: str, model_zip_file_path: str
+    ):
         """
         Add Statements text for non Apache-2.0 licensed third party model. Add it to the model zip file at model_zip_file_path
 
@@ -785,7 +787,7 @@ def save_as_pt(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
-        third_party_copyrights_statements: Optional[str] = None
+        third_party_copyrights_statements: Optional[str] = None,
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to torch script format,
@@ -822,10 +824,12 @@ def save_as_pt(
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
-        
+
         if add_apache_license == True and not third_party_copyrights_statements is None:
-            assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
-            
+            assert (
+                False
+            ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
+
         model = SentenceTransformer(model_id)
 
         if model_name is None:
@@ -891,7 +895,9 @@ def save_as_pt(
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
         if not third_party_copyrights_statements is None:
-            self._add_third_party_copyrights_statements_to_model_zip_file(third_party_copyrights_statements, zip_file_path)
+            self._add_third_party_copyrights_statements_to_model_zip_file(
+                third_party_copyrights_statements, zip_file_path
+            )
 
         self.torch_script_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
@@ -905,7 +911,7 @@ def save_as_onnx(
         model_output_path: str = None,
         zip_file_name: str = None,
         add_apache_license: bool = False,
-        third_party_copyrights_statements: Optional[str] = None
+        third_party_copyrights_statements: Optional[str] = None,
     ) -> str:
         """
         Download sentence transformer model directly from huggingface, convert model to onnx format,
@@ -939,9 +945,11 @@ def save_as_onnx(
         :return: model zip file path. The file path where the zip file is being saved
         :rtype: string
         """
-        
+
         if add_apache_license == True and not third_party_copyrights_statements is None:
-            assert False, "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
+            assert (
+                False
+            ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
 
         model = SentenceTransformer(model_id)
 
@@ -997,7 +1005,9 @@ def save_as_onnx(
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
         if not third_party_copyrights_statements is None:
-            self._add_third_party_copyrights_statements_to_model_zip_file(third_party_copyrights_statements, zip_file_path)
+            self._add_third_party_copyrights_statements_to_model_zip_file(
+                third_party_copyrights_statements, zip_file_path
+            )
 
         self.onnx_zip_file_path = zip_file_path
         print("zip file is saved to ", zip_file_path, "\n")
@@ -1334,9 +1344,9 @@ def make_model_config_json(
                 model_config_content["model_content_size_in_bytes"] = os.stat(
                     model_zip_file_path
                 ).st_size
-                model_config_content["model_content_hash_value"] = (
-                    _generate_model_content_hash_value(model_zip_file_path)
-                )
+                model_config_content[
+                    "model_content_hash_value"
+                ] = _generate_model_content_hash_value(model_zip_file_path)
 
         if verbose:
             print("generating ml-commons_model_config.json file...\n")
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 4fa9545df..d7c967ad3 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -32,7 +32,9 @@
 from opensearch_py_ml.ml_commons import MLCommonClient
 from opensearch_py_ml.ml_models.sentencetransformermodel import SentenceTransformerModel
 from tests import OPENSEARCH_TEST_CLIENT
-from third_party_statements import generate_thirdpart_statements_for_MIT
+from third_party_statements import (
+    generate_thirdpart_statements_for_huggingface_MIT_models,
+)
 
 BOTH_FORMAT = "BOTH"
 TORCH_SCRIPT_FORMAT = "TORCH_SCRIPT"
@@ -80,9 +82,14 @@ def verify_license_in_md_file(model_license: str = "Apache-2.0") -> bool:
         print(f"\nFound {model_license} license at " + TEMP_MODEL_PATH + "/README.md")
         return True
     else:
-        print(f"\nDid not find {model_license} license at " + TEMP_MODEL_PATH + "/README.md")
+        print(
+            f"\nDid not find {model_license} license at "
+            + TEMP_MODEL_PATH
+            + "/README.md"
+        )
         return False
 
+
 def trace_sentence_transformer_model(
     model_id: str,
     model_license: str,
@@ -91,7 +98,7 @@ def trace_sentence_transformer_model(
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
-    third_party_copyrights_statements: Optional[str] = None
+    third_party_copyrights_statements: Optional[str] = None,
 ) -> Tuple[str, str]:
     """
     Trace the pretrained sentence transformer model, create a model config file,
@@ -141,14 +148,14 @@ def trace_sentence_transformer_model(
             model_path = pre_trained_model.save_as_pt(
                 model_id=model_id,
                 sentences=TEST_SENTENCES,
-                add_apache_license=model_license=="Apache-2.0",
-                third_party_copyrights_statements=third_party_copyrights_statements
+                add_apache_license=model_license == "Apache-2.0",
+                third_party_copyrights_statements=third_party_copyrights_statements,
             )
         else:
             model_path = pre_trained_model.save_as_onnx(
                 model_id=model_id,
-                add_apache_license=model_license=="Apache-2.0",
-                third_party_copyrights_statements=third_party_copyrights_statements
+                add_apache_license=model_license == "Apache-2.0",
+                third_party_copyrights_statements=third_party_copyrights_statements,
             )
     except Exception as e:
         assert False, f"Raised Exception during saving model as {model_format}: {e}"
@@ -422,7 +429,7 @@ def main(
     embedding_dimension: Optional[int] = None,
     pooling_mode: Optional[str] = None,
     model_description: Optional[str] = None,
-    third_party_copyrights_statements: Optional[str] = None
+    third_party_copyrights_statements: Optional[str] = None,
 ) -> None:
     """
     Perform model auto-tracing and prepare files for uploading to OpenSearch model hub
@@ -462,8 +469,10 @@ def main(
         model_description if model_description is not None else "N/A",
     )
     print(
-        "Third Party Statements Text: ", 
-        third_party_copyrights_statements if third_party_copyrights_statements is not None else "N/A"
+        "Third Party Statements Text: ",
+        third_party_copyrights_statements
+        if third_party_copyrights_statements is not None
+        else "N/A",
     )
     print("==========================================")
 
@@ -494,7 +503,7 @@ def main(
             embedding_dimension,
             pooling_mode,
             model_description,
-            third_party_copyrights_statements
+            third_party_copyrights_statements,
         )
 
         torchscript_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -526,10 +535,7 @@ def main(
 
     if tracing_format in [ONNX_FORMAT, BOTH_FORMAT]:
         print("--- Begin tracing a model in ONNX ---")
-        (
-            onnx_model_path,
-            onnx_model_config_path,
-        ) = trace_sentence_transformer_model(
+        (onnx_model_path, onnx_model_config_path,) = trace_sentence_transformer_model(
             model_id,
             model_license,
             model_version,
@@ -537,7 +543,7 @@ def main(
             embedding_dimension,
             pooling_mode,
             model_description,
-            third_party_copyrights_statements
+            third_party_copyrights_statements,
         )
 
         onnx_embedding_data = register_and_deploy_sentence_transformer_model(
@@ -621,17 +627,22 @@ def main(
         help="Model description if you want to overwrite the default description",
     )
     parser.add_argument(
-        "-tpcs",
-        "--third_party_copyrights_statements",
+        "-mlu",
+        "--mit_license_url",
         type=str,
         nargs="?",
         default=None,
         const=None,
-        help="Copyright statement for MIT licensed models.",
+        help="MIT license url",
     )
-    
+
     args = parser.parse_args()
-        
+
+    third_party_copyrights_statements = (
+        generate_thirdpart_statements_for_huggingface_MIT_models(
+            args.model_id, args.mit_license_url
+        )
+    )
     main(
         args.model_id,
         args.model_license,
@@ -640,5 +651,5 @@ def main(
         args.embedding_dimension,
         args.pooling_mode,
         args.model_description,
-        args.third_party_copyrights_statements
+        third_party_copyrights_statements,
     )
diff --git a/utils/model_uploader/third_party_statements.py b/utils/model_uploader/third_party_statements.py
index 6c24640b1..924b3c571 100644
--- a/utils/model_uploader/third_party_statements.py
+++ b/utils/model_uploader/third_party_statements.py
@@ -4,57 +4,31 @@
 # compatible open source license.
 # Any modifications Copyright OpenSearch Contributors. See
 # GitHub history for details.
-from string import Template
+import re
+import requests
 
-MIT_TEMPLATE = Template("""
-** $model_id; version $model_version $attribution_website
-$copyright_statement
- 
-MIT License
 
-$copyright_statement
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
-""")
-
-def generate_thirdpart_statements_for_MIT(
-    model_id: str,
-    copyright_statement: str, 
-    attribution_website: str, 
-    model_version:str
+def generate_thirdpart_statements_for_huggingface_MIT_models(
+    model_id: str, mit_license_url: str
 ) -> str:
     """
-    Generate statements text for MIT-licensed third party model. The result should be put in the final artifact.
-    
+    Generate statements text for huggingface MIT-licensed third party model. The result should be put in the final artifact.
+
     :param model_id: Model ID of the pretrained model
     :type model_id: string
-    :param copyright_statement: MIT models copyright statement
-    :type copyright_statement: string
-    :param attribution_website: The project website for MIT licensed models
-    :type attribution_website: string
-    :param model_version: The model version for MIT licensed models
-    :type model_version: string
-    :return: Statements text for MIT-licensed third party model.
+    :param mit_license_url: the url of the model's MIT license
+    :type mit_license_url: string
     :rtype: str
     """
-    
-    
-    result = MIT_TEMPLATE.substitute(model_id=model_id, copyright_statement=copyright_statement,
-                                     attribution_website=attribution_website, model_version=model_version)
-    return result.strip()
\ No newline at end of file
+
+    r = requests.get(mit_license_url)
+    assert r.status_code == 200, "Failed to add license file to the model zip file"
+    license_text = r.content.decode("utf-8")
+
+    # find the copyright statements from origin MIT license. It looks like: Copyright (c) {year} {authorname}
+    copyright_statements = re.findall("Copyright.*\n", license_text)[0].strip()
+    huggingface_url = "https://huggingface.co/" + model_id
+
+    full_statements = f"** {model_id}; version  -- {huggingface_url}\n{copyright_statements}\n\n{license_text}"
+
+    return full_statements

From e997594f63f084822cb4742598538fcdd0186b20 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 08:31:47 +0000
Subject: [PATCH 13/23] lint

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml          |  2 +-
 opensearch_py_ml/field_mappings.py            |  6 +++---
 opensearch_py_ml/ml_commons/model_uploader.py |  6 +++---
 .../metrics_correlation/event_detection.py    |  6 +++---
 .../ml_models/sentencetransformermodel.py     | 14 ++++++-------
 utils/model_uploader/model_autotracing.py     | 20 ++++++++++++-------
 .../model_uploader/third_party_statements.py  |  1 +
 7 files changed, 31 insertions(+), 24 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 39d6353f0..013840836 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -58,7 +58,7 @@ on:
         - "NO"
         - "YES"
       MIT_license_url:
-        description: "(Optional) MIT license of the huggingface MIT model."
+        description: "(Optional) MIT license url of the huggingface MIT model."
         required: false
         type: string
 
diff --git a/opensearch_py_ml/field_mappings.py b/opensearch_py_ml/field_mappings.py
index b3c83914a..75bbd1833 100644
--- a/opensearch_py_ml/field_mappings.py
+++ b/opensearch_py_ml/field_mappings.py
@@ -445,9 +445,9 @@ def find_aggregatable(row, df):
                 try:
                     series = df.loc[df.os_field_name == os_field_name_keyword]
                     if not series.empty and series.is_aggregatable.squeeze():
-                        row_as_dict[
-                            "aggregatable_os_field_name"
-                        ] = os_field_name_keyword
+                        row_as_dict["aggregatable_os_field_name"] = (
+                            os_field_name_keyword
+                        )
                     else:
                         row_as_dict["aggregatable_os_field_name"] = None
                 except KeyError:
diff --git a/opensearch_py_ml/ml_commons/model_uploader.py b/opensearch_py_ml/ml_commons/model_uploader.py
index af7af2f62..850f6a80a 100644
--- a/opensearch_py_ml/ml_commons/model_uploader.py
+++ b/opensearch_py_ml/ml_commons/model_uploader.py
@@ -95,9 +95,9 @@ def _register_model(
         model_meta_json[TOTAL_CHUNKS_FIELD] = total_num_chunks
 
         if MODEL_CONTENT_SIZE_IN_BYTES_FIELD not in model_meta_json:
-            model_meta_json[
-                MODEL_CONTENT_SIZE_IN_BYTES_FIELD
-            ] = model_content_size_in_bytes
+            model_meta_json[MODEL_CONTENT_SIZE_IN_BYTES_FIELD] = (
+                model_content_size_in_bytes
+            )
         if MODEL_CONTENT_HASH_VALUE not in model_meta_json:
             # Generate the sha1 hash for the model zip file
             hash_val_model_file = _generate_model_content_hash_value(model_path)
diff --git a/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py b/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
index f9395d1a4..f6e5187cd 100644
--- a/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
+++ b/opensearch_py_ml/ml_models/metrics_correlation/event_detection.py
@@ -94,9 +94,9 @@ def merge_events(
     send = ends[ix]
     sevents = candidates[ix, :]
 
-    merged: List[
-        Dict[str, torch.Tensor]
-    ] = []  # merge in linear pass over time dimension
+    merged: List[Dict[str, torch.Tensor]] = (
+        []
+    )  # merge in linear pass over time dimension
     currstart = torch.tensor([-1])
     currend = torch.tensor([-1])
     currevent = torch.ones(T) * -1.0
diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index 63e3e6e56..c37b30479 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -825,7 +825,7 @@ def save_as_pt(
         :rtype: string
         """
 
-        if add_apache_license == True and not third_party_copyrights_statements is None:
+        if add_apache_license == True and third_party_copyrights_statements is not None:
             assert (
                 False
             ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
@@ -894,7 +894,7 @@ def save_as_pt(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
-        if not third_party_copyrights_statements is None:
+        if third_party_copyrights_statements is not None:
             self._add_third_party_copyrights_statements_to_model_zip_file(
                 third_party_copyrights_statements, zip_file_path
             )
@@ -946,7 +946,7 @@ def save_as_onnx(
         :rtype: string
         """
 
-        if add_apache_license == True and not third_party_copyrights_statements is None:
+        if add_apache_license == True and third_party_copyrights_statements is not None:
             assert (
                 False
             ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
@@ -1004,7 +1004,7 @@ def save_as_onnx(
             )
         if add_apache_license:
             self._add_apache_license_to_model_zip_file(zip_file_path)
-        if not third_party_copyrights_statements is None:
+        if third_party_copyrights_statements is not None:
             self._add_third_party_copyrights_statements_to_model_zip_file(
                 third_party_copyrights_statements, zip_file_path
             )
@@ -1344,9 +1344,9 @@ def make_model_config_json(
                 model_config_content["model_content_size_in_bytes"] = os.stat(
                     model_zip_file_path
                 ).st_size
-                model_config_content[
-                    "model_content_hash_value"
-                ] = _generate_model_content_hash_value(model_zip_file_path)
+                model_config_content["model_content_hash_value"] = (
+                    _generate_model_content_hash_value(model_zip_file_path)
+                )
 
         if verbose:
             print("generating ml-commons_model_config.json file...\n")
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index d7c967ad3..0ba1355bb 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -29,13 +29,14 @@
 ROOT_DIR = os.path.join(THIS_DIR, "../..")
 sys.path.append(ROOT_DIR)
 
-from opensearch_py_ml.ml_commons import MLCommonClient
-from opensearch_py_ml.ml_models.sentencetransformermodel import SentenceTransformerModel
-from tests import OPENSEARCH_TEST_CLIENT
 from third_party_statements import (
     generate_thirdpart_statements_for_huggingface_MIT_models,
 )
 
+from opensearch_py_ml.ml_commons import MLCommonClient
+from opensearch_py_ml.ml_models.sentencetransformermodel import SentenceTransformerModel
+from tests import OPENSEARCH_TEST_CLIENT
+
 BOTH_FORMAT = "BOTH"
 TORCH_SCRIPT_FORMAT = "TORCH_SCRIPT"
 ONNX_FORMAT = "ONNX"
@@ -470,9 +471,11 @@ def main(
     )
     print(
         "Third Party Statements Text: ",
-        third_party_copyrights_statements
-        if third_party_copyrights_statements is not None
-        else "N/A",
+        (
+            third_party_copyrights_statements
+            if third_party_copyrights_statements is not None
+            else "N/A"
+        ),
     )
     print("==========================================")
 
@@ -535,7 +538,10 @@ def main(
 
     if tracing_format in [ONNX_FORMAT, BOTH_FORMAT]:
         print("--- Begin tracing a model in ONNX ---")
-        (onnx_model_path, onnx_model_config_path,) = trace_sentence_transformer_model(
+        (
+            onnx_model_path,
+            onnx_model_config_path,
+        ) = trace_sentence_transformer_model(
             model_id,
             model_license,
             model_version,
diff --git a/utils/model_uploader/third_party_statements.py b/utils/model_uploader/third_party_statements.py
index 924b3c571..0603b5a47 100644
--- a/utils/model_uploader/third_party_statements.py
+++ b/utils/model_uploader/third_party_statements.py
@@ -5,6 +5,7 @@
 # Any modifications Copyright OpenSearch Contributors. See
 # GitHub history for details.
 import re
+
 import requests
 
 

From 08540b270d4c5e4b9142f473d11b613d5e0584f8 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 09:16:28 +0000
Subject: [PATCH 14/23] improve error log

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml             | 8 ++++----
 opensearch_py_ml/ml_commons/ml_commons_client.py | 5 +++--
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index 013840836..b0a06fe4b 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -295,7 +295,7 @@ jobs:
       - name: Create Issue Body
         id: create_issue_body
         run: |    
-          issue_body='Please approve or deny opensearch-py-ml model uploading:
+          issue_body="Please approve or deny opensearch-py-ml model uploading:
           
           ${{ needs.model-auto-tracing.outputs.license_line }}
           
@@ -303,7 +303,7 @@ jobs:
           ${{ needs.model-auto-tracing.outputs.model_description_info }}
           
           ===== Dry Run of Model Uploading =====
-          ${{ needs.model-auto-tracing.outputs.dryrun_output }}'
+          ${{ needs.model-auto-tracing.outputs.dryrun_output }}"
 
           echo "issue_body<<EOF" >> $GITHUB_OUTPUT
           echo "${issue_body@E}" >> $GITHUB_OUTPUT
@@ -380,14 +380,14 @@ jobs:
       - name: Create PR Body
         id: create_pr_body
         run: |
-          pr_body='
+          pr_body="
           - [ ] This PR made commit to only these three files: MODEL_UPLOAD_HISTORY.md, supported_models.json, and CHANGELOG.md.
           - [ ] CHANGELOG.md has been updated by the workflow or by you if the workflow fails to do so. 
           - [ ] Merge conflicts have been resolved.
           
           ${{ needs.init-workflow-var.outputs.workflow_info }}
           ${{ needs.model-auto-tracing.outputs.license_info }}
-          ${{ needs.model-auto-tracing.outputs.model_description_info }}'
+          ${{ needs.model-auto-tracing.outputs.model_description_info }}"
           
           echo "pr_body<<EOF" >> $GITHUB_OUTPUT
           echo "${pr_body@E}" >> $GITHUB_OUTPUT
diff --git a/opensearch_py_ml/ml_commons/ml_commons_client.py b/opensearch_py_ml/ml_commons/ml_commons_client.py
index 8b50a95cc..8dec28829 100644
--- a/opensearch_py_ml/ml_commons/ml_commons_client.py
+++ b/opensearch_py_ml/ml_commons/ml_commons_client.py
@@ -371,7 +371,7 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             for i in range(TIMEOUT):
                 ml_model_status = self.get_model_info(model_id)
                 model_state = ml_model_status.get("model_state")
-                if model_state in ["DEPLOYED", "PARTIALLY_DEPLOYED"]:
+                if model_state in ["DEPLOYED", "PARTIALLY_DEPLOYED", "DEPLOY_FAILED"]:
                     break
                 time.sleep(1)
 
@@ -382,7 +382,8 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             elif model_state == "PARTIALLY_DEPLOYED":
                 print("Model deployed only partially")
             else:
-                raise Exception("Model deployment failed, model_state:", model_state)
+                raise Exception("Model deployment failed, model_state:", model_state, 
+                                "task info:",self.get_task_info(task_id))
 
         return self._get_task_info(task_id)
 

From 98794e04c7144b3bc4558145a752d1cb3d41690a Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Thu, 25 Apr 2024 09:51:45 +0000
Subject: [PATCH 15/23] lint

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 opensearch_py_ml/ml_commons/ml_commons_client.py |  5 ++---
 utils/model_uploader/model_autotracing.py        | 10 +++++-----
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/opensearch_py_ml/ml_commons/ml_commons_client.py b/opensearch_py_ml/ml_commons/ml_commons_client.py
index 8dec28829..2f387ad11 100644
--- a/opensearch_py_ml/ml_commons/ml_commons_client.py
+++ b/opensearch_py_ml/ml_commons/ml_commons_client.py
@@ -371,7 +371,7 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             for i in range(TIMEOUT):
                 ml_model_status = self.get_model_info(model_id)
                 model_state = ml_model_status.get("model_state")
-                if model_state in ["DEPLOYED", "PARTIALLY_DEPLOYED", "DEPLOY_FAILED"]:
+                if model_state in ["DEPLOYED", "PARTIALLY_DEPLOYED"]:
                     break
                 time.sleep(1)
 
@@ -382,8 +382,7 @@ def deploy_model(self, model_id: str, wait_until_deployed: bool = True) -> objec
             elif model_state == "PARTIALLY_DEPLOYED":
                 print("Model deployed only partially")
             else:
-                raise Exception("Model deployment failed, model_state:", model_state, 
-                                "task info:",self.get_task_info(task_id))
+                raise Exception("Model deployment failed")
 
         return self._get_task_info(task_id)
 
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 0ba1355bb..6d755dd3f 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -643,12 +643,12 @@ def main(
     )
 
     args = parser.parse_args()
-
-    third_party_copyrights_statements = (
-        generate_thirdpart_statements_for_huggingface_MIT_models(
-            args.model_id, args.mit_license_url
+    if args.model_license == "MIT":
+        third_party_copyrights_statements = (
+            generate_thirdpart_statements_for_huggingface_MIT_models(
+                args.model_id, args.mit_license_url
+            )
         )
-    )
     main(
         args.model_id,
         args.model_license,

From 70f0713fcf8a248bb4210a6105ca76d41234f61b Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 02:40:02 +0000
Subject: [PATCH 16/23] fix

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 utils/model_uploader/model_autotracing.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 6d755dd3f..3d2b8767b 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -649,6 +649,9 @@ def main(
                 args.model_id, args.mit_license_url
             )
         )
+    else:
+        third_party_copyrights_statements = None
+
     main(
         args.model_id,
         args.model_license,

From fe0471a020a90b7b94b91c206ebcc49a2c81b32d Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 04:56:55 +0000
Subject: [PATCH 17/23] add test

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .../test_sentencetransformermodel_pytest.py   | 79 +++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/tests/ml_models/test_sentencetransformermodel_pytest.py b/tests/ml_models/test_sentencetransformermodel_pytest.py
index 17f86c75b..ba3cad9cd 100644
--- a/tests/ml_models/test_sentencetransformermodel_pytest.py
+++ b/tests/ml_models/test_sentencetransformermodel_pytest.py
@@ -221,6 +221,26 @@ def test_missing_files():
     assert "Cannot find config.json" in str(exc_info.value)
 
 
+def test_save_model_but_license_conflicts():
+    with pytest.raises(AssertionError) as exc_info:
+        test_model.save_as_pt(
+            sentences=["today is sunny"], add_apache_license=True, third_party_copyrights_statements="test statements"
+        )
+    assert (
+        "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
+        in str(exc_info.value)
+    )
+
+    with pytest.raises(AssertionError) as exc_info:
+        test_model.save_as_onnx(
+            add_apache_license=True, third_party_copyrights_statements="test statements"
+        )
+    assert (
+        "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
+        in str(exc_info.value)
+    )
+
+
 def test_save_as_pt():
     try:
         test_model.save_as_pt(sentences=["today is sunny"])
@@ -658,5 +678,64 @@ def test_zip_model_with_license():
     clean_test_folder(TEST_FOLDER)
 
 
+def test_save_as_pt_with_third_party_copyrights_statements():
+    model_id = "sentence-transformers/all-MiniLM-L6-v2"
+    model_format = "TORCH_SCRIPT"
+    torch_script_zip_file_path = os.path.join(TEST_FOLDER, "all-MiniLM-L6-v2.zip")
+    torch_script_expected_filenames = {
+        "all-MiniLM-L6-v2.pt",
+        "tokenizer.json",
+        "THIRD-PARTY",
+    }
+
+    clean_test_folder(TEST_FOLDER)
+    test_model18 = SentenceTransformerModel(
+        folder_path=TEST_FOLDER,
+        model_id=model_id,
+    )
+    third_party_copyrights_statements = "test statements"
+
+    test_model18.save_as_pt(
+        model_id=model_id,
+        sentences=["today is sunny"],
+        third_party_copyrights_statements=third_party_copyrights_statements,
+    )
+
+    compare_model_zip_file(
+        torch_script_zip_file_path, torch_script_expected_filenames, model_format
+    )
+
+    clean_test_folder(TEST_FOLDER)
+
+
+def test_save_as_onnx_with_third_party_copyrights_statements():
+    model_id = "sentence-transformers/all-MiniLM-L6-v2"
+    model_format = "TORCH_SCRIPT"
+    torch_script_zip_file_path = os.path.join(TEST_FOLDER, "all-MiniLM-L6-v2.zip")
+    torch_script_expected_filenames = {
+        "all-MiniLM-L6-v2.pt",
+        "tokenizer.json",
+        "THIRD-PARTY",
+    }
+
+    clean_test_folder(TEST_FOLDER)
+    test_model19 = SentenceTransformerModel(
+        folder_path=TEST_FOLDER,
+        model_id=model_id,
+    )
+    third_party_copyrights_statements = "test statements"
+
+    test_model19.save_as_onnx(
+        model_id=model_id,
+        third_party_copyrights_statements=third_party_copyrights_statements,
+    )
+
+    compare_model_zip_file(
+        torch_script_zip_file_path, torch_script_expected_filenames, model_format
+    )
+
+    clean_test_folder(TEST_FOLDER)
+
+
 clean_test_folder(TEST_FOLDER)
 clean_test_folder(TESTDATA_UNZIP_FOLDER)

From db4900226cd7ad687f9d69c1105f1a0adef3acb2 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 05:00:37 +0000
Subject: [PATCH 18/23] lint

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 tests/ml_models/test_sentencetransformermodel_pytest.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tests/ml_models/test_sentencetransformermodel_pytest.py b/tests/ml_models/test_sentencetransformermodel_pytest.py
index ba3cad9cd..beee4127e 100644
--- a/tests/ml_models/test_sentencetransformermodel_pytest.py
+++ b/tests/ml_models/test_sentencetransformermodel_pytest.py
@@ -224,7 +224,9 @@ def test_missing_files():
 def test_save_model_but_license_conflicts():
     with pytest.raises(AssertionError) as exc_info:
         test_model.save_as_pt(
-            sentences=["today is sunny"], add_apache_license=True, third_party_copyrights_statements="test statements"
+            sentences=["today is sunny"],
+            add_apache_license=True,
+            third_party_copyrights_statements="test statements",
         )
     assert (
         "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."

From 4200890470ec3a5722124f2ad0c7f8fedd5f9a83 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 05:03:20 +0000
Subject: [PATCH 19/23] changelog

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index adac4dbf7..e3980ffa8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 - Add support for model profiles by @rawwar in ([#358](https://github.com/opensearch-project/opensearch-py-ml/pull/358))
 - Support for security default admin credential changes in 2.12.0 in ([#365](https://github.com/opensearch-project/opensearch-py-ml/pull/365))
 - adding cross encoder models in the pre-trained traced list ([#378](https://github.com/opensearch-project/opensearch-py-ml/pull/378))
+- adding support for upload huggingface MIT licensed models ([](https://github.com/opensearch-project/opensearch-py-ml/pull/))
 
 
 ### Changed

From 34a18d6a7266fde36b5e35cc4326da7f4ea4ab7b Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 08:55:48 +0000
Subject: [PATCH 20/23] finalize

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .github/workflows/model_uploader.yml             | 16 ++++++++--------
 CHANGELOG.md                                     |  2 +-
 .../test_sentencetransformermodel_pytest.py      |  2 +-
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index b0a06fe4b..ff2724eb0 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -309,14 +309,14 @@ jobs:
           echo "${issue_body@E}" >> $GITHUB_OUTPUT
           echo "EOF" >> $GITHUB_OUTPUT
           echo "${issue_body@E}"
-      # - uses: trstringer/manual-approval@v1
-      #   with:
-      #     secret: ${{ github.TOKEN }}
-      #     approvers: ${{ steps.get_approvers.outputs.approvers }}
-      #     minimum-approvals: 2
-      #     issue-title: "Upload Model to OpenSearch Model Hub (${{ github.event.inputs.model_id }})"
-      #     issue-body: ${{ steps.create_issue_body.outputs.issue_body }}
-      #     exclude-workflow-initiator-as-approver: false
+      - uses: trstringer/manual-approval@v1
+        with:
+          secret: ${{ github.TOKEN }}
+          approvers: ${{ steps.get_approvers.outputs.approvers }}
+          minimum-approvals: 2
+          issue-title: "Upload Model to OpenSearch Model Hub (${{ github.event.inputs.model_id }})"
+          issue-body: ${{ steps.create_issue_body.outputs.issue_body }}
+          exclude-workflow-initiator-as-approver: false
       
   # Step 6: Download the artifacts & Upload it to the S3 bucket
   model-uploading:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index e3980ffa8..7589a646b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,7 +14,7 @@ Inspired from [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 - Add support for model profiles by @rawwar in ([#358](https://github.com/opensearch-project/opensearch-py-ml/pull/358))
 - Support for security default admin credential changes in 2.12.0 in ([#365](https://github.com/opensearch-project/opensearch-py-ml/pull/365))
 - adding cross encoder models in the pre-trained traced list ([#378](https://github.com/opensearch-project/opensearch-py-ml/pull/378))
-- adding support for upload huggingface MIT licensed models ([](https://github.com/opensearch-project/opensearch-py-ml/pull/))
+- adding support for upload huggingface MIT licensed models ([388](https://github.com/opensearch-project/opensearch-py-ml/pull/388))
 
 
 ### Changed
diff --git a/tests/ml_models/test_sentencetransformermodel_pytest.py b/tests/ml_models/test_sentencetransformermodel_pytest.py
index beee4127e..1528739d1 100644
--- a/tests/ml_models/test_sentencetransformermodel_pytest.py
+++ b/tests/ml_models/test_sentencetransformermodel_pytest.py
@@ -715,7 +715,7 @@ def test_save_as_onnx_with_third_party_copyrights_statements():
     model_format = "TORCH_SCRIPT"
     torch_script_zip_file_path = os.path.join(TEST_FOLDER, "all-MiniLM-L6-v2.zip")
     torch_script_expected_filenames = {
-        "all-MiniLM-L6-v2.pt",
+        "all-MiniLM-L6-v2.onnx",
         "tokenizer.json",
         "THIRD-PARTY",
     }

From 5f6e71442e33648a6dbc06cec29e7734f7655316 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Fri, 26 Apr 2024 10:22:24 +0000
Subject: [PATCH 21/23] lint

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 opensearch_py_ml/ml_models/sentencetransformermodel.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index c37b30479..a93ceaead 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -829,7 +829,6 @@ def save_as_pt(
             assert (
                 False
             ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
-
         model = SentenceTransformer(model_id)
 
         if model_name is None:
@@ -950,7 +949,6 @@ def save_as_onnx(
             assert (
                 False
             ), "When the model is from third party under non Apache-2.0 license, we can not add Apache-2.0 license for it."
-
         model = SentenceTransformer(model_id)
 
         if model_name is None:

From 5da6ae9302d249e8d60f42fb37fa01f3254ff5b4 Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Mon, 13 May 2024 03:07:59 +0000
Subject: [PATCH 22/23] change third_party to static var

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 opensearch_py_ml/ml_models/sentencetransformermodel.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/opensearch_py_ml/ml_models/sentencetransformermodel.py b/opensearch_py_ml/ml_models/sentencetransformermodel.py
index a93ceaead..eb5375bd6 100644
--- a/opensearch_py_ml/ml_models/sentencetransformermodel.py
+++ b/opensearch_py_ml/ml_models/sentencetransformermodel.py
@@ -38,6 +38,7 @@
 )
 
 LICENSE_URL = "https://github.com/opensearch-project/opensearch-py-ml/raw/main/LICENSE"
+THIRD_PARTY_FILE_NAME = "THIRD-PARTY"
 
 
 class SentenceTransformerModel:
@@ -671,7 +672,7 @@ def _add_third_party_copyrights_statements_to_model_zip_file(
         :rtype: None
         """
         with ZipFile(str(model_zip_file_path), "a") as zipObj:
-            zipObj.writestr("THIRD-PARTY", third_party_copyrights_statements)
+            zipObj.writestr(THIRD_PARTY_FILE_NAME, third_party_copyrights_statements)
 
     def zip_model(
         self,

From 4f6af15d1870c75467fed1147a299d62e6f7299b Mon Sep 17 00:00:00 2001
From: zhichao-aws <zhichaog@amazon.com>
Date: Tue, 14 May 2024 07:02:20 +0000
Subject: [PATCH 23/23] change mit_license to addtional license

Signed-off-by: zhichao-aws <zhichaog@amazon.com>
---
 .ci/run-repository.sh                     |  4 ++--
 .github/workflows/model_uploader.yml      | 16 ++++++++--------
 utils/model_uploader/model_autotracing.py |  8 ++++----
 3 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/.ci/run-repository.sh b/.ci/run-repository.sh
index b3b6974eb..30e721e50 100755
--- a/.ci/run-repository.sh
+++ b/.ci/run-repository.sh
@@ -74,7 +74,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   echo -e "\033[34;1mINFO:\033[0m EMBEDDING_DIMENSION: ${EMBEDDING_DIMENSION:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m POOLING_MODE: ${POOLING_MODE:-N/A}\033[0m"
   echo -e "\033[34;1mINFO:\033[0m MODEL_DESCRIPTION: ${MODEL_DESCRIPTION:-N/A}\033[0m"
-  echo -e "\033[34;1mINFO:\033[0m MIT_LICENSE_URL: ${MIT_LICENSE_URL:-N/A}\033[0m"
+  echo -e "\033[34;1mINFO:\033[0m ADDITIONAL_LICENSE_URL: ${ADDITIONAL_LICENSE_URL:-N/A}\033[0m"
 
   docker run \
   --network=${network_name} \
@@ -87,7 +87,7 @@ elif [[ "$TASK_TYPE" == "trace" ]]; then
   --name opensearch-py-ml-trace-runner \
   opensearch-project/opensearch-py-ml \
   nox -s "trace-${PYTHON_VERSION}" -- ${MODEL_ID} ${MODEL_LICENSE} ${MODEL_VERSION} ${TRACING_FORMAT} -ed ${EMBEDDING_DIMENSION} -pm ${POOLING_MODE} \
-   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -mlu ${MIT_LICENSE_URL}
+   -md ${MODEL_DESCRIPTION:+"$MODEL_DESCRIPTION"} -alu ${ADDITIONAL_LICENSE_URL}
   
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/upload/ ./upload/
   docker cp opensearch-py-ml-trace-runner:/code/opensearch-py-ml/trace_output/ ./trace_output/
diff --git a/.github/workflows/model_uploader.yml b/.github/workflows/model_uploader.yml
index ff2724eb0..4995b6e52 100644
--- a/.github/workflows/model_uploader.yml
+++ b/.github/workflows/model_uploader.yml
@@ -57,8 +57,8 @@ on:
         options:
         - "NO"
         - "YES"
-      MIT_license_url:
-        description: "(Optional) MIT license url of the huggingface MIT model."
+      additional_license_url:
+        description: "(Optional) Additional license url of the huggingface MIT model."
         required: false
         type: string
 
@@ -84,7 +84,7 @@ jobs:
         embedding_dimension=${{ github.event.inputs.embedding_dimension }}
         pooling_mode=${{ github.event.inputs.pooling_mode }}
         model_description="${{ github.event.inputs.model_description }}"
-        MIT_license_url="${{ github.event.inputs.MIT_license_url }}"
+        additional_license_url="${{ github.event.inputs.additional_license_url }}"
         
         workflow_info="
         ============= Workflow Details ==============
@@ -101,7 +101,7 @@ jobs:
         - Embedding Dimension: ${embedding_dimension:-N/A}
         - Pooling Mode: ${pooling_mode:-N/A}
         - Model Description: ${model_description:-N/A}
-        - MIT License Url: ${MIT_license_url:-N/A}
+        - Additional License Url: ${additional_license_url:-N/A}
         
         ======== Workflow Output Information =========
         - Embedding Verification: Passed"
@@ -110,13 +110,13 @@ jobs:
         echo "${workflow_info@E}" >> $GITHUB_OUTPUT
         echo "EOF" >> $GITHUB_OUTPUT
         echo "${workflow_info@E}"
-    - name: Check MIT license url
-      id: check_mit_license_url
+    - name: Check Additional license url
+      id: check_additional_license_url
       run: |
         if [[ "${{ github.event.inputs.model_license }}" == "MIT" ]]
         then
           echo "Uploading MIT licensed model"
-          if [[ "${{ github.event.inputs.MIT_license_url }}" == "" ]]
+          if [[ "${{ github.event.inputs.additional_license_url }}" == "" ]]
           then
               echo "missing MIT license url"
               exit 1
@@ -214,7 +214,7 @@ jobs:
           echo "EMBEDDING_DIMENSION=${{ github.event.inputs.embedding_dimension }}" >> $GITHUB_ENV
           echo "POOLING_MODE=${{ github.event.inputs.pooling_mode }}" >> $GITHUB_ENV     
           echo "MODEL_DESCRIPTION=${{ github.event.inputs.model_description }}" >> $GITHUB_ENV
-          echo "MIT_LICENSE_URL=${{ github.event.inputs.MIT_license_url }}" >> $GITHUB_ENV
+          echo "ADDITIONAL_LICENSE_URL=${{ github.event.inputs.additional_license_url }}" >> $GITHUB_ENV
       - name: Autotracing ${{ matrix.cluster }} secured=${{ matrix.secured }} version=${{matrix.entry.opensearch_version}}
         run: "./.ci/run-tests ${{ matrix.cluster }} ${{ matrix.secured }} ${{ matrix.entry.opensearch_version }} trace"
       - name: Limit Model Size to 2GB
diff --git a/utils/model_uploader/model_autotracing.py b/utils/model_uploader/model_autotracing.py
index 3d2b8767b..a482ad681 100644
--- a/utils/model_uploader/model_autotracing.py
+++ b/utils/model_uploader/model_autotracing.py
@@ -633,20 +633,20 @@ def main(
         help="Model description if you want to overwrite the default description",
     )
     parser.add_argument(
-        "-mlu",
-        "--mit_license_url",
+        "-alu",
+        "--additional_license_url",
         type=str,
         nargs="?",
         default=None,
         const=None,
-        help="MIT license url",
+        help="Additional license url",
     )
 
     args = parser.parse_args()
     if args.model_license == "MIT":
         third_party_copyrights_statements = (
             generate_thirdpart_statements_for_huggingface_MIT_models(
-                args.model_id, args.mit_license_url
+                args.model_id, args.additional_license_url
             )
         )
     else: