onnxruntime_extensions 0.12.0__cp38-cp38-win_amd64.whl → 0.13.0__cp38-cp38-win_amd64.whl

onnxruntime_extensions/_hf_cvt.py

@@ -48,8 +48,9 @@ class HFTokenizerConverter(CustomOpConverter):
             model_dir = hf_tokenizer.name_or_path
         else:
             model_dir = os.path.dirname(vocab_file)
-        tokenizer_json = json.load(
-            open(os.path.join(model_dir, tokenizer_file), "r", encoding="utf-8"))
+        f = open(os.path.join(model_dir, tokenizer_file), "r", encoding="utf-8")
+        tokenizer_json = json.load(f)
+        f.close()
         # get vocab object from json file
         vocab = tokenizer_json.get("model", {}).get("vocab", {})
         sorted_merges = tokenizer_json.get("model", {}).get("merges", [])

onnxruntime_extensions/_version.py

@@ -1,2 +1,2 @@
 # Generated by setup.py, DON'T MANUALLY UPDATE IT!
-__version__ = "0.12.0"
+__version__ = "0.13.0"

onnxruntime_extensions/pp_api.py

@@ -3,11 +3,79 @@
 # license information.
 ###############################################################################
 
+import os
 from . import _extensions_pydll as _C
-if not hasattr(_C, "create_processor"):
-    raise ImportError("onnxruntime_extensions is not built with pre-processing API")
+if not hasattr(_C, "delete_object"):
+    raise ImportError(
+        "onnxruntime_extensions is not built with pre-processing C API\n"
+        "To enable it, please build the package with --ortx-user-option=pp_api")
 
 create_processor = _C.create_processor
 load_images = _C.load_images
 image_pre_process = _C.image_pre_process
 tensor_result_get_at = _C.tensor_result_get_at
+
+create_tokenizer = _C.create_tokenizer
+batch_tokenize = _C.batch_tokenize
+batch_detokenize = _C.batch_detokenize
+
+delete_object = _C.delete_object
+
+
+class Tokenizer:
+    def __init__(self, tokenizer_dir):
+        self.tokenizer = None
+        if os.path.isdir(tokenizer_dir):
+            self.tokenizer = create_tokenizer(tokenizer_dir)
+        else:
+            try:
+                from transformers.utils import cached_file
+                resolved_full_file = cached_file(
+                    tokenizer_dir, "tokenizer.json")
+                resolved_config_file = cached_file(
+                    tokenizer_dir, "tokenizer_config.json")
+            except ImportError:
+                raise ValueError(
+                    f"Directory '{tokenizer_dir}' not found and transformers is not available")
+            if not os.path.exists(resolved_full_file):
+                raise FileNotFoundError(
+                    f"Downloaded HF file '{resolved_full_file}' cannot be found")
+            if (os.path.dirname(resolved_full_file) != os.path.dirname(resolved_config_file)):
+                raise FileNotFoundError(
+                    f"Downloaded HF files '{resolved_full_file}' "
+                    f"and '{resolved_config_file}' are not in the same directory")
+
+            tokenizer_dir = os.path.dirname(resolved_full_file)
+            self.tokenizer = create_tokenizer(tokenizer_dir)
+
+    def tokenize(self, text):
+        return batch_tokenize(self.tokenizer, [text])[0]
+
+    def detokenize(self, tokens):
+        return batch_detokenize(self.tokenizer, [tokens])[0]
+
+    def __del__(self):
+        if delete_object and self.tokenizer:
+            delete_object(self.tokenizer)
+        self.tokenizer = None
+
+
+class ImageProcessor:
+    def __init__(self, processor_json):
+        self.processor = create_processor(processor_json)
+
+    def pre_process(self, images):
+        if isinstance(images, str):
+            images = [images]
+        if isinstance(images, list):
+            images = load_images(images)
+        return image_pre_process(self.processor, images)
+
+    @staticmethod
+    def to_numpy(result):
+        return tensor_result_get_at(result, 0)
+
+    def __del__(self):
+        if delete_object and self.processor:
+            delete_object(self.processor)
+        self.processor = None

{onnxruntime_extensions-0.12.0.dist-info → onnxruntime_extensions-0.13.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxruntime_extensions
-Version: 0.12.0
+Version: 0.13.0
 Summary: ONNXRuntime Extensions
 Home-page: https://github.com/microsoft/onnxruntime-extensions
 Author: Microsoft Corporation
@@ -25,29 +25,17 @@ License-File: LICENSE
 
 ## What's ONNXRuntime-Extensions
 
-Introduction: ONNXRuntime-Extensions is a library that extends the capability of the ONNX models and inference with ONNX Runtime, via ONNX Runtime Custom Operator ABIs. It includes a set of [ONNX Runtime Custom Operator](https://onnxruntime.ai/docs/reference/operators/add-custom-op.html) to support the common pre- and post-processing operators for vision, text, and nlp models. And it supports multiple languages and platforms, like Python on Windows/Linux/macOS, some mobile platforms like Android and iOS, and Web-Assembly etc. The basic workflow is to enhance a ONNX model firstly and then do the model inference with ONNX Runtime and ONNXRuntime-Extensions package.
+Introduction: ONNXRuntime-Extensions is a C/C++ library that extends the capability of the ONNX models and inference with ONNX Runtime, via ONNX Runtime Custom Operator ABIs. It includes a set of [ONNX Runtime Custom Operator](https://onnxruntime.ai/docs/reference/operators/add-custom-op.html) to support the common pre- and post-processing operators for vision, text, and nlp models. And it supports multiple languages and platforms, like Python on Windows/Linux/macOS, some mobile platforms like Android and iOS, and Web-Assembly etc. The basic workflow is to enhance a ONNX model firstly and then do the model inference with ONNX Runtime and ONNXRuntime-Extensions package.
 
 
 ## Quickstart
+The library can be utilized as either a C/C++ library or other advance language packages like Python, Java, C#, etc. To build it as a shared library, you can use the `build.bat` or `build.sh` scripts located in the root folder. The CMake build definition is available in the `CMakeLists.txt` file and can be modified by appending options to `build.bat` or `build.sh`, such as `build.bat -DOCOS_BUILD_SHARED_LIB=OFF`. For more details, please refer to the [C API documentation](./docs/c_api.md).
 
 ### **Python installation**
 ```bash
 pip install onnxruntime-extensions
 ````
-
-
-### **Nightly Build**
-
-#### <strong>on Windows</strong>
-```cmd
-pip install --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple/ onnxruntime-extensions
-```
-Please ensure that you have met the prerequisites of onnxruntime-extensions (e.g., onnx and onnxruntime) in your Python environment.
-#### <strong>on Linux/macOS</strong>
-Please make sure the compiler toolkit like gcc(later than g++ 8.0) or clang are installed before the following command
-```bash
-python -m pip install git+https://github.com/microsoft/onnxruntime-extensions.git
-```
+The nightly build is also available for the latest features, please refer to [nightly build](./docs/development.md#nightly-build)
 
 
 ## Usage

{onnxruntime_extensions-0.12.0.dist-info → onnxruntime_extensions-0.13.0.dist-info}/RECORD

@@ -1,15 +1,15 @@
 onnxruntime_extensions/__init__.py,sha256=GMnMIHJ-uqvJGPn5fpCZOi7OG16kFVpfOTTO88kYJWY,2387
 onnxruntime_extensions/_cuops.py,sha256=SUD2NhEWHeMem8ylCtCGBKutSuZQs4WMj1ke65-52vA,16193
-onnxruntime_extensions/_extensions_pydll.cp38-win_amd64.pyd,sha256=pCpIiDFVl9d21JFt2MqodExtFfu0tOL4wCczwOwFu_8,3329024
+onnxruntime_extensions/_extensions_pydll.cp38-win_amd64.pyd,sha256=OEPzg22-fhVPxJYurDncDJaIwZ7WSqFDMoaeYyZabyU,3379712
 onnxruntime_extensions/_extensions_pydll.pyi,sha256=mYXkqNaCgAbs161RDKgDjxIX9vWdYdVPDC-0X9cieco,1070
-onnxruntime_extensions/_hf_cvt.py,sha256=HJwpcdc02aYV9qgAYkrtSYbkargYi0xTqf7Ye60D84A,14062
+onnxruntime_extensions/_hf_cvt.py,sha256=3RDEr4uga_FYBReSDgqLqvj_2-7HgVOk073BRT8lK_E,14082
 onnxruntime_extensions/_ocos.py,sha256=OlDOlCH_vWFOBkjbp6Pujgw6rgk8Fd3_2Mi5ev1eeS0,4193
 onnxruntime_extensions/_ortapi2.py,sha256=Tfrf9fQMQ0e7Wa4R8s4SHdwMNBdmj33wH3y5vMkVVQE,9951
 onnxruntime_extensions/_torch_cvt.py,sha256=hGOiw24QuFpK_3CLjg8Fs2GD_cCdM049xcJxkHVRbAk,10185
-onnxruntime_extensions/_version.py,sha256=gjGFlfLnfAn2djJsgIststV0PRkvMcSSr51ENp79FDA,76
+onnxruntime_extensions/_version.py,sha256=uFV2Hf2pKZgA12fk8O9oCxhl_fUheVDYuvrK3A-Vjnc,76
 onnxruntime_extensions/cmd.py,sha256=eIiNNY0ohbUCPgmr9RwOfi0Gzw7nWL17i625L-ZKezI,2428
 onnxruntime_extensions/cvt.py,sha256=XMz0CZXBJQ9IwnixjzJwz-utKyu9HREIEUCviZg6v8A,3977
-onnxruntime_extensions/pp_api.py,sha256=-Qty5kyN0stBft6vecPucGnjQLZXQd_8PzaCvcQM6ys,571
+onnxruntime_extensions/pp_api.py,sha256=MpW3frODcWXOmYaoTQiYWiM807rC8GjlWgpIYc-CDy8,3051
 onnxruntime_extensions/util.py,sha256=KxNFY0-5CG1i9HADcCc4V33PNukTO46Os_KIL8pj-l8,7394
 onnxruntime_extensions/onnxprocess/__init__.py,sha256=BnveHXnu2nTQNbCLeZujZgZwO9A3yWFbQGTDthCFbIc,534
 onnxruntime_extensions/onnxprocess/_builder.py,sha256=L_afKeE7Wc4mWJ47eVXQ2stvmal_37QVTQZgKmt0ZK8,1844
@@ -36,8 +36,8 @@ onnxruntime_extensions/tools/pre_post_processing/steps/__init__.py,sha256=pdVRZB
 onnxruntime_extensions/tools/pre_post_processing/steps/general.py,sha256=fF_XVFSKOCu482Sqjp-nVPbs-ZVGpPal2ekbO1gUO_4,13781
 onnxruntime_extensions/tools/pre_post_processing/steps/nlp.py,sha256=ZCxRNxqfANplxCe0I-6BfHziM1jDYJsNQKbHdM3Y1I0,15173
 onnxruntime_extensions/tools/pre_post_processing/steps/vision.py,sha256=BM6CGylOSu4l6UarPfW0I2tgkJDa1Q-gYz__CxZle-k,53183
-onnxruntime_extensions-0.12.0.dist-info/LICENSE,sha256=mQaUD2Gx8LUz-n2ZuvVReLKAj74RPqUd-_rYVyzNXys,1162
-onnxruntime_extensions-0.12.0.dist-info/METADATA,sha256=ulMfUUUKIosCAUeqozJAJ5LQbpnQsU6HvsvbA-_tTXA,4452
-onnxruntime_extensions-0.12.0.dist-info/WHEEL,sha256=6DUGimnTtl3rU6RGwkmZI1NHXBFbwPul6M-9UShD9rs,99
-onnxruntime_extensions-0.12.0.dist-info/top_level.txt,sha256=XyAgQDKyXsf6_0MJb58kRdHwigpTn7A7kl9diBEjs8M,23
-onnxruntime_extensions-0.12.0.dist-info/RECORD,,
+onnxruntime_extensions-0.13.0.dist-info/LICENSE,sha256=mQaUD2Gx8LUz-n2ZuvVReLKAj74RPqUd-_rYVyzNXys,1162
+onnxruntime_extensions-0.13.0.dist-info/METADATA,sha256=MmpoFbjh5Etph2BR7msz-Nrg6QNh56wtGqL46NUSiaE,4483
+onnxruntime_extensions-0.13.0.dist-info/WHEEL,sha256=BiKefS7XHc6W0zY4ROW4fxXTZBRH27JLKtM6pqE4hBs,99
+onnxruntime_extensions-0.13.0.dist-info/top_level.txt,sha256=XyAgQDKyXsf6_0MJb58kRdHwigpTn7A7kl9diBEjs8M,23
+onnxruntime_extensions-0.13.0.dist-info/RECORD,,

{onnxruntime_extensions-0.12.0.dist-info → onnxruntime_extensions-0.13.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (72.2.0)
+Generator: setuptools (75.2.0)
 Root-Is-Purelib: false
 Tag: cp38-cp38-win_amd64