PyPI - spacy - Versions diffs - 4.0.0.dev2__tar.gz → 4.0.0.dev3__tar.gz - Mend

spacy 4.0.0.dev2tar.gz → 4.0.0.dev3tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (968) hide show

{spacy-4.0.0.dev2/spacy.egg-info → spacy-4.0.0.dev3}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacy
-Version: 4.0.0.dev2
+Version: 4.0.0.dev3
 Summary: Industrial-strength Natural Language Processing (NLP) in Python
 Home-page: https://spacy.io
 Author: Explosion
@@ -18,20 +18,20 @@ Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: Microsoft :: Windows
 Classifier: Programming Language :: Cython
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: >=3.8
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: spacy-legacy<4.1.0,>=4.0.0.dev0
+Requires-Dist: spacy-legacy<4.1.0,>=4.0.0.dev1
 Requires-Dist: spacy-loggers<2.0.0,>=1.0.0
 Requires-Dist: murmurhash<1.1.0,>=0.28.0
 Requires-Dist: cymem<2.1.0,>=2.0.2
 Requires-Dist: preshed<3.1.0,>=3.0.2
-Requires-Dist: thinc<9.1.0,>=9.0.0.dev4
+Requires-Dist: thinc<9.1.0,>=9.0.0
 Requires-Dist: wasabi<1.2.0,>=0.9.1
 Requires-Dist: srsly<3.0.0,>=2.4.3
 Requires-Dist: catalogue<2.1.0,>=2.0.6
@@ -89,8 +89,6 @@ Provides-Extra: cuda12x
 Requires-Dist: cupy-cuda12x<13.0.0,>=11.5.0; extra == "cuda12x"
 Provides-Extra: cuda-autodetect
 Requires-Dist: cupy-wheel<13.0.0,>=11.0.0; extra == "cuda-autodetect"
-Provides-Extra: apple
-Requires-Dist: thinc-apple-ops<1.0.0,>=0.1.0.dev0; extra == "apple"
 Provides-Extra: ja
 Requires-Dist: sudachipy!=0.6.1,>=0.5.2; extra == "ja"
 Requires-Dist: sudachidict_core>=20211220; extra == "ja"
@@ -133,25 +131,25 @@ open-source software, released under the
 ## 📖 Documentation
-| Documentation                                                                                                                                                                                                             |                                                                                                                                                                                                                                                                                                                                              |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ⭐️ **[spaCy 101]**                                                                                                                                                                                                       | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                                                            |
-| 📚 **[Usage Guides]**                                                                                                                                                                                                     | How to use spaCy and its features.                                                                                                                                                                                                                                                                                                           |
-| 🚀 **[New in v3.0]**                                                                                                                                                                                                      | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                                                               |
-| 🪐 **[Project Templates]**                                                                                                                                                                                                | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                                                          |
-| 🎛 **[API Reference]**                                                                                                                                                                                                     | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                                                                      |
-| ⏩ **[GPU Processing]**                                                                                                                                                                                                    | Use spaCy with CUDA-compatible GPU processing.                                                                                                                                                                                                                                                                                               |
-| 📦 **[Models]**                                                                                                                                                                                                           | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                                                        |
-| 🦙 **[Large Language Models]**                                                                                                                                                                                            | Integrate LLMs into spaCy pipelines.                                                                                                                                                                                                                                                                                                        |
-| 🌌 **[Universe]**                                                                                                                                                                                                         | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                                                               |
-| ⚙️ **[spaCy VS Code Extension]**                                                                                                                                                                                          | Additional tooling and features for working with spaCy's config files.                                                                                                                                                                                                                                                                       |
-| 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                                      |
-| 📰 **[Blog]**                                                                                                                                                                                                             | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                                 |
-| 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                                    |
-| 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                                 |
-| 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                                        |
-| 👕 **[Swag]**                                                                                                                                                                                                             | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                                                                   |
-| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)**                 |
+| Documentation                                                                                                                                                                                   |                                                                                                                                                                                                                                                                                                       |
+| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ⭐️ **[spaCy 101]**                                                                                                                                                                             | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                     |
+| 📚 **[Usage Guides]**                                                                                                                                                                           | How to use spaCy and its features.                                                                                                                                                                                                                                                                    |
+| 🚀 **[New in v3.0]**                                                                                                                                                                            | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                        |
+| 🪐 **[Project Templates]**                                                                                                                                                                      | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                   |
+| 🎛 **[API Reference]**                                                                                                                                                                           | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                               |
+| ⏩ **[GPU Processing]**                                                                                                                                                                         | Use spaCy with CUDA-compatible GPU processing.                                                                                                                                                                                                                                                        |
+| 📦 **[Models]**                                                                                                                                                                                 | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                 |
+| 🦙 **[Large Language Models]**                                                                                                                                                                  | Integrate LLMs into spaCy pipelines.                                                                                                                                                                                                                                                                  |
+| 🌌 **[Universe]**                                                                                                                                                                               | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                        |
+| ⚙️ **[spaCy VS Code Extension]**                                                                                                                                                                | Additional tooling and features for working with spaCy's config files.                                                                                                                                                                                                                                |
+| 👩‍🏫 **[Online Course]**                                                                                                                                                                          | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                               |
+| 📰 **[Blog]**                                                                                                                                                                                   | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                            |
+| 📺 **[Videos]**                                                                                                                                                                                 | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                             |
+| 🛠 **[Changelog]**                                                                                                                                                                               | Changes and version history.                                                                                                                                                                                                                                                                          |
+| 💝 **[Contribute]**                                                                                                                                                                             | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                 |
+| 👕 **[Swag]**                                                                                                                                                                                   | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                            |
+| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)** |
 [spacy 101]: https://spacy.io/usage/spacy-101
 [new in v3.0]: https://spacy.io/usage/v3
@@ -216,7 +214,7 @@ For detailed installation instructions, see the
 - **Operating system**: macOS / OS X · Linux · Windows (Cygwin, MinGW, Visual
   Studio)
-- **Python version**: Python 3.8+ (only 64 bit)
+- **Python version**: Python 3.9+ (only 64 bit)
 - **Package managers**: [pip] · [conda] (via `conda-forge`)
 [pip]: https://pypi.org/project/spacy/

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/README.md RENAMED Viewed

@@ -32,25 +32,25 @@ open-source software, released under the
 ## 📖 Documentation
-| Documentation                                                                                                                                                                                                             |                                                                                                                                                                                                                                                                                                                                              |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ⭐️ **[spaCy 101]**                                                                                                                                                                                                       | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                                                            |
-| 📚 **[Usage Guides]**                                                                                                                                                                                                     | How to use spaCy and its features.                                                                                                                                                                                                                                                                                                           |
-| 🚀 **[New in v3.0]**                                                                                                                                                                                                      | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                                                               |
-| 🪐 **[Project Templates]**                                                                                                                                                                                                | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                                                          |
-| 🎛 **[API Reference]**                                                                                                                                                                                                     | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                                                                      |
-| ⏩ **[GPU Processing]**                                                                                                                                                                                                    | Use spaCy with CUDA-compatible GPU processing.                                                                                                                                                                                                                                                                                               |
-| 📦 **[Models]**                                                                                                                                                                                                           | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                                                        |
-| 🦙 **[Large Language Models]**                                                                                                                                                                                            | Integrate LLMs into spaCy pipelines.                                                                                                                                                                                                                                                                                                        |
-| 🌌 **[Universe]**                                                                                                                                                                                                         | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                                                               |
-| ⚙️ **[spaCy VS Code Extension]**                                                                                                                                                                                          | Additional tooling and features for working with spaCy's config files.                                                                                                                                                                                                                                                                       |
-| 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                                      |
-| 📰 **[Blog]**                                                                                                                                                                                                             | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                                 |
-| 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                                    |
-| 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                                 |
-| 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                                        |
-| 👕 **[Swag]**                                                                                                                                                                                                             | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                                                                   |
-| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)**                 |
+| Documentation                                                                                                                                                                                   |                                                                                                                                                                                                                                                                                                       |
+| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ⭐️ **[spaCy 101]**                                                                                                                                                                             | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                     |
+| 📚 **[Usage Guides]**                                                                                                                                                                           | How to use spaCy and its features.                                                                                                                                                                                                                                                                    |
+| 🚀 **[New in v3.0]**                                                                                                                                                                            | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                        |
+| 🪐 **[Project Templates]**                                                                                                                                                                      | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                   |
+| 🎛 **[API Reference]**                                                                                                                                                                           | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                               |
+| ⏩ **[GPU Processing]**                                                                                                                                                                         | Use spaCy with CUDA-compatible GPU processing.                                                                                                                                                                                                                                                        |
+| 📦 **[Models]**                                                                                                                                                                                 | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                 |
+| 🦙 **[Large Language Models]**                                                                                                                                                                  | Integrate LLMs into spaCy pipelines.                                                                                                                                                                                                                                                                  |
+| 🌌 **[Universe]**                                                                                                                                                                               | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                        |
+| ⚙️ **[spaCy VS Code Extension]**                                                                                                                                                                | Additional tooling and features for working with spaCy's config files.                                                                                                                                                                                                                                |
+| 👩‍🏫 **[Online Course]**                                                                                                                                                                          | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                               |
+| 📰 **[Blog]**                                                                                                                                                                                   | Read about current spaCy and Prodigy development, releases, talks and more from Explosion.                                                                                                                                                                                                            |
+| 📺 **[Videos]**                                                                                                                                                                                 | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                             |
+| 🛠 **[Changelog]**                                                                                                                                                                               | Changes and version history.                                                                                                                                                                                                                                                                          |
+| 💝 **[Contribute]**                                                                                                                                                                             | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                 |
+| 👕 **[Swag]**                                                                                                                                                                                   | Support us and our work with unique, custom-designed swag!                                                                                                                                                                                                                                            |
+| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more &rarr;](https://explosion.ai/tailored-solutions)** |
 [spacy 101]: https://spacy.io/usage/spacy-101
 [new in v3.0]: https://spacy.io/usage/v3
@@ -115,7 +115,7 @@ For detailed installation instructions, see the
 - **Operating system**: macOS / OS X · Linux · Windows (Cygwin, MinGW, Visual
   Studio)
-- **Python version**: Python 3.8+ (only 64 bit)
+- **Python version**: Python 3.9+ (only 64 bit)
 - **Package managers**: [pip] · [conda] (via `conda-forge`)
 [pip]: https://pypi.org/project/spacy/

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/pyproject.toml RENAMED Viewed

@@ -5,7 +5,7 @@ requires = [
     "cymem>=2.0.2,<2.1.0",
     "preshed>=3.0.2,<3.1.0",
     "murmurhash>=0.28.0,<1.1.0",
-    "thinc>=9.0.0.dev4,<9.1.0",
+    "thinc>=9.0.0,<9.1.0",
     "numpy>=1.15.0; python_version < '3.9'",
     "numpy>=1.25.0; python_version >= '3.9'",
 ]

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/setup.cfg RENAMED Viewed

@@ -17,10 +17,10 @@ classifiers =
 	Operating System :: Microsoft :: Windows
 	Programming Language :: Cython
 	Programming Language :: Python :: 3
-	Programming Language :: Python :: 3.8
 	Programming Language :: Python :: 3.9
 	Programming Language :: Python :: 3.10
 	Programming Language :: Python :: 3.11
+	Programming Language :: Python :: 3.12
 	Topic :: Scientific/Engineering
 project_urls =
 	Release notes = https://github.com/explosion/spaCy/releases
@@ -29,14 +29,14 @@ project_urls =
 [options]
 zip_safe = false
 include_package_data = true
-python_requires = >=3.8
+python_requires = >=3.9
 install_requires =
-	spacy-legacy>=4.0.0.dev0,<4.1.0
+	spacy-legacy>=4.0.0.dev1,<4.1.0
 	spacy-loggers>=1.0.0,<2.0.0
 	murmurhash>=0.28.0,<1.1.0
 	cymem>=2.0.2,<2.1.0
 	preshed>=3.0.2,<3.1.0
-	thinc>=9.0.0.dev4,<9.1.0
+	thinc>=9.0.0,<9.1.0
 	wasabi>=0.9.1,<1.2.0
 	srsly>=2.4.3,<3.0.0
 	catalogue>=2.0.6,<2.1.0
@@ -100,8 +100,6 @@ cuda12x =
 	cupy-cuda12x>=11.5.0,<13.0.0
 cuda-autodetect =
 	cupy-wheel>=11.0.0,<13.0.0
-apple =
-	thinc-apple-ops>=0.1.0.dev0,<1.0.0
 ja =
 	sudachipy>=0.5.2,!=0.6.1
 	sudachidict_core>=20211220

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/about.py RENAMED Viewed

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "4.0.0.dev2"
+__version__ = "4.0.0.dev3"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/cli/__init__.py RENAMED Viewed

@@ -12,6 +12,7 @@ from .debug_config import debug_config  # noqa: F401
 from .debug_data import debug_data  # noqa: F401
 from .debug_diff import debug_diff  # noqa: F401
 from .debug_model import debug_model  # noqa: F401
+from .distill import distill  # noqa: F401
 from .download import download  # noqa: F401
 from .evaluate import evaluate  # noqa: F401
 from .find_function import find_function  # noqa: F401

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/cli/benchmark_speed.py RENAMED Viewed

@@ -13,7 +13,7 @@ from .. import util
 from ..language import Language
 from ..tokens import Doc
 from ..training import Corpus
-from ._util import Arg, Opt, benchmark_cli, setup_gpu
+from ._util import Arg, Opt, benchmark_cli, import_code, setup_gpu
 @benchmark_cli.command(
@@ -30,12 +30,14 @@ def benchmark_speed_cli(
     use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
     n_batches: int = Opt(50, "--batches", help="Minimum number of batches to benchmark", min=30,),
     warmup_epochs: int = Opt(3, "--warmup", "-w", min=0, help="Number of iterations over the data for warmup"),
+    code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
     # fmt: on
 ):
     """
     Benchmark a pipeline. Expects a loadable spaCy pipeline and benchmark
     data in the binary .spacy format.
     """
+    import_code(code_path)
     setup_gpu(use_gpu=use_gpu, silent=False)
     nlp = util.load_model(model)
@@ -171,5 +173,5 @@ def print_outliers(sample: numpy.ndarray):
 def warmup(
     nlp: Language, docs: List[Doc], warmup_epochs: int, batch_size: Optional[int]
 ) -> numpy.ndarray:
-    docs = warmup_epochs * docs
+    docs = [doc.copy() for doc in docs * warmup_epochs]
     return annotate(nlp, docs, batch_size)

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/cli/debug_data.py RENAMED Viewed

@@ -1073,8 +1073,7 @@ def _get_distribution(docs, normalize: bool = True) -> Counter:
     word_counts: Counter = Counter()
     for doc in docs:
         for token in doc:
-            # Normalize the text
-            t = token.text.lower().replace("``", '"').replace("''", '"')
+            t = token.text.lower()
             word_counts[t] += 1
     if normalize:
         total = sum(word_counts.values(), 0.0)

spacy-4.0.0.dev3/spacy/cli/distill.py ADDED Viewed

@@ -0,0 +1,98 @@
+import logging
+import sys
+from pathlib import Path
+from typing import Any, Dict, Optional, Union
+import typer
+from wasabi import msg
+from .. import util
+from ..pipeline.trainable_pipe import TrainablePipe
+from ..schemas import ConfigSchemaDistill
+from ..training.initialize import init_nlp_student
+from ..training.loop import distill as distill_nlp
+from ._util import (
+    Arg,
+    Opt,
+    app,
+    import_code_paths,
+    parse_config_overrides,
+    setup_gpu,
+    show_validation_error,
+)
+@app.command(
+    "distill",
+    context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
+)
+def distill_cli(
+    # fmt: off
+    ctx: typer.Context,  # This is only used to read additional arguments
+    teacher_model: str = Arg(..., help="Teacher model name or path"),
+    student_config_path: Path = Arg(..., help="Path to config file", exists=True, allow_dash=True),
+    output_path: Optional[Path] = Opt(None, "--output", "--output-path", "-o", help="Output directory to store trained pipeline in"),
+    code_path: str = Opt("", "--code", "-c", help="Comma-separated paths to Python files with additional code (registered functions) to be imported"),
+    verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
+    use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU")
+    # fmt: on
+):
+    """
+    Distill a spaCy pipeline from a teacher model.
+    DOCS: https://spacy.io/api/cli#distill
+    """
+    util.logger.setLevel(logging.DEBUG if verbose else logging.INFO)
+    overrides = parse_config_overrides(ctx.args)
+    import_code_paths(code_path)
+    distill(
+        teacher_model,
+        student_config_path,
+        output_path,
+        use_gpu=use_gpu,
+        overrides=overrides,
+    )
+def distill(
+    teacher_model: Union[str, Path],
+    student_config_path: Union[str, Path],
+    output_path: Optional[Union[str, Path]] = None,
+    *,
+    use_gpu: int = -1,
+    overrides: Dict[str, Any] = util.SimpleFrozenDict(),
+):
+    student_config_path = util.ensure_path(student_config_path)
+    output_path = util.ensure_path(output_path)
+    # Make sure all files and paths exist if they are needed
+    if not student_config_path or (
+        str(student_config_path) != "-" and not student_config_path.exists()
+    ):
+        msg.fail("Student config file not found", student_config_path, exits=1)
+    if not output_path:
+        msg.info("No output directory provided")
+    else:
+        if not output_path.exists():
+            output_path.mkdir(parents=True)
+            msg.good(f"Created output directory: {output_path}")
+        msg.info(f"Saving to output directory: {output_path}")
+    setup_gpu(use_gpu)
+    teacher = util.load_model(teacher_model)
+    with show_validation_error(student_config_path):
+        config = util.load_config(
+            student_config_path, overrides=overrides, interpolate=False
+        )
+    msg.divider("Initializing student pipeline")
+    with show_validation_error(student_config_path, hint_fill=False):
+        student = init_nlp_student(config, teacher, use_gpu=use_gpu)
+    msg.good("Initialized student pipeline")
+    msg.divider("Distilling student pipeline from teacher")
+    distill_nlp(
+        teacher,
+        student,
+        output_path,
+        use_gpu=use_gpu,
+        stdout=sys.stdout,
+        stderr=sys.stderr,
+    )

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/cli/templates/quickstart_training.jinja RENAMED Viewed

@@ -238,7 +238,7 @@ grad_factor = 1.0
 {% if "entity_linker" in components -%}
 [components.entity_linker]
 factory = "entity_linker"
-get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
+get_candidates = {"@misc":"spacy.CandidateGenerator.v2"}
 incl_context = true
 incl_prior = true
@@ -517,7 +517,7 @@ width = ${components.tok2vec.model.encode.width}
 {% if "entity_linker" in components -%}
 [components.entity_linker]
 factory = "entity_linker"
-get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
+get_candidates = {"@misc":"spacy.CandidateGenerator.v2"}
 incl_context = true
 incl_prior = true

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/errors.py RENAMED Viewed

@@ -950,7 +950,6 @@ class Errors(metaclass=ErrorsWithCodes):
              "case pass an empty list for the previously not specified argument to avoid this error.")
     E1043 = ("Expected None or a value in range [{range_start}, {range_end}] for entity linker threshold, but got "
              "{value}.")
-    E1044 = ("Expected `candidates_batch_size` to be >= 1, but got: {value}")
     E1045 = ("Encountered {parent} subclass without `{parent}.{method}` "
              "method in '{name}'. If you want to use this method, make "
              "sure it's overwritten on the subclass.")

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/git_info.py RENAMED Viewed

@@ -1,3 +1,3 @@
 # THIS FILE IS GENERATED FROM SPACY SETUP.PY
 #
-GIT_VERSION = "ce9ea9629"
+GIT_VERSION = "f5918d435"

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/kb/kb.pyx RENAMED Viewed

@@ -1,14 +1,14 @@
 # cython: infer_types=True
 from pathlib import Path
-from typing import Iterable, Tuple, Union
+from typing import Iterable, Iterator, Tuple, Union
 from cymem.cymem cimport Pool
 from ..errors import Errors
-from ..tokens import Span, SpanGroup
+from ..tokens import SpanGroup
 from ..util import SimpleFrozenList
-from .candidate import Candidate
+from .candidate cimport Candidate
 cdef class KnowledgeBase:
@@ -19,6 +19,8 @@ cdef class KnowledgeBase:
     DOCS: https://spacy.io/api/kb
     """
+    CandidatesForMentionT = Iterable[Candidate]
+    CandidatesForDocT = Iterable[CandidatesForMentionT]
     def __init__(self, vocab: Vocab, entity_vector_length: int):
         """Create a KnowledgeBase."""
@@ -32,27 +34,15 @@ cdef class KnowledgeBase:
         self.entity_vector_length = entity_vector_length
         self.mem = Pool()
-    def get_candidates_batch(
-            self, mentions: SpanGroup
-    ) -> Iterable[Iterable[Candidate]]:
+    def get_candidates(self, mentions: Iterator[SpanGroup]) -> Iterator[CandidatesForDocT]:
         """
-        Return candidate entities for a specified Span mention. Each candidate defines at least the entity and the
-        entity's embedding vector. Depending on the KB implementation, further properties - such as the prior
-        probability of the specified mention text resolving to that entity - might be included.
+        Return candidate entities for the specified groups of mentions (as SpanGroup) per Doc.
+        Each candidate for a mention defines at least the entity and the entity's embedding vector. Depending on the KB
+        implementation, further properties - such as the prior probability of the specified mention text resolving to
+        that entity - might be included.
         If no candidates are found for a given mention, an empty list is returned.
-        mentions (SpanGroup): Mentions for which to get candidates.
-        RETURNS (Iterable[Iterable[Candidate]]): Identified candidates.
-        """
-        return [self.get_candidates(span) for span in mentions]
-    def get_candidates(self, mention: Span) -> Iterable[Candidate]:
-        """
-        Return candidate entities for a specific mention. Each candidate defines at least the entity and the
-        entity's embedding vector. Depending on the KB implementation, further properties - such as the prior
-        probability of the specified mention text resolving to that entity - might be included.
-        If no candidate is found for the given mention, an empty list is returned.
-        mention (Span): Mention for which to get candidates.
-        RETURNS (Iterable[Candidate]): Identified candidates.
+        mentions (Iterator[SpanGroup]): Mentions for which to get candidates.
+        RETURNS (Iterator[Iterable[Iterable[Candidate]]]): Identified candidates per mention/doc/doc batch.
         """
         raise NotImplementedError(
             Errors.E1045.format(

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/kb/kb_in_memory.pyx RENAMED Viewed

@@ -1,5 +1,5 @@
 # cython: infer_types=True
-from typing import Any, Callable, Dict, Iterable
+from typing import Any, Callable, Dict, Iterable, Iterator
 import srsly
@@ -12,7 +12,7 @@ from preshed.maps cimport PreshMap
 import warnings
 from pathlib import Path
-from ..tokens import Span
+from ..tokens import SpanGroup
 from ..typedefs cimport hash_t
@@ -255,8 +255,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
             alias_entry.probs = probs
             self._aliases_table[alias_index] = alias_entry
-    def get_candidates(self, mention: Span) -> Iterable[InMemoryCandidate]:
-        return self._get_alias_candidates(mention.text)  # type: ignore
+    def get_candidates(self, mentions: Iterator[SpanGroup]) -> Iterator[Iterable[Iterable[InMemoryCandidate]]]:
+        for mentions_for_doc in mentions:
+            yield [self._get_alias_candidates(span.text) for span in mentions_for_doc]
     def _get_alias_candidates(self, str alias) -> Iterable[InMemoryCandidate]:
         """

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/language.py RENAMED Viewed

@@ -1830,6 +1830,7 @@ class Language:
             # is done, so that they can exit gracefully.
             for q in texts_q:
                 q.put(_WORK_DONE_SENTINEL)
+                q.close()
             # Otherwise, we are stopping because the error handler raised an
             # exception. The sentinel will be last to go out of the queue.
@@ -2464,7 +2465,8 @@ def _apply_pipes(
             # Stop working if we encounter the end-of-work sentinel.
             if isinstance(texts_with_ctx, _WorkDoneSentinel):
-                return
+                sender.close()
+                receiver.close()
             docs = (
                 ensure_doc(doc_like, context) for doc_like, context in texts_with_ctx
@@ -2488,7 +2490,8 @@ def _apply_pipes(
             # Parent has closed the pipe prematurely. This happens when a
             # worker encounters an error and the error handler is set to
             # stop processing.
-            return
+            sender.close()
+            receiver.close()
 class _Sender:

{spacy-4.0.0.dev2 → spacy-4.0.0.dev3}/spacy/matcher/levenshtein.c RENAMED Viewed

@@ -4,13 +4,13 @@
 {
     "distutils": {
         "depends": [
-            "/opt/hostedtoolcache/Python/3.8.18/x64/include/python3.8/Python.h",
+            "/opt/hostedtoolcache/Python/3.9.19/x64/include/python3.9/Python.h",
             "spacy/matcher/polyleven.c"
         ],
         "include_dirs": [
             "spacy/matcher",
-            "/tmp/build-env-v58t4koh/lib/python3.8/site-packages/numpy/core/include",
-            "/opt/hostedtoolcache/Python/3.8.18/x64/include/python3.8"
+            "/tmp/build-env-zum2hv36/lib/python3.9/site-packages/numpy/core/include",
+            "/opt/hostedtoolcache/Python/3.9.19/x64/include/python3.9"
         ],
         "language": "c",
         "name": "spacy.matcher.levenshtein",

spacy 4.0.0.dev2__tar.gz → 4.0.0.dev3__tar.gz

spacy 4.0.0.dev2tar.gz → 4.0.0.dev3tar.gz