Merge branch 'master' into docs/memory-management

Author: ines

.github/workflows/tests.yml

@@ -12,7 +12,6 @@ on:
       - "*.md"
       - "*.mdx"
       - "website/**"
-      - ".github/workflows/**"
   pull_request:
     types: [opened, synchronize, reopened, edited]
     paths-ignore:
@@ -32,7 +31,7 @@ jobs:
       - name: Configure Python version
         uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
+          python-version: "3.10"
 
       - name: black
         run: |
@@ -59,18 +58,7 @@ jobs:
       fail-fast: true
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python_version: ["3.12"]
-        include:
-          - os: windows-latest
-            python_version: "3.7"
-          - os: macos-latest
-            python_version: "3.8"
-          - os: ubuntu-latest
-            python_version: "3.9"
-          - os: windows-latest
-            python_version: "3.10"
-          - os: macos-latest
-            python_version: "3.11"
+        python_version: ["3.9", "3.11", "3.12"]
 
     runs-on: ${{ matrix.os }}
 
@@ -159,7 +147,9 @@ jobs:
       - name: "Test assemble CLI"
         run: |
           python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
-          PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
+          python -m spacy assemble ner_source_sm.cfg output_dir
+        env:
+          PYTHONWARNINGS: "error,ignore::DeprecationWarning" 
         if: matrix.python_version == '3.9'
 
       - name: "Test assemble CLI vectors warning"

CONTRIBUTING.md

@@ -35,7 +35,7 @@ so that more people can benefit from it.
 
 When opening an issue, use a **descriptive title** and include your
 **environment** (operating system, Python version, spaCy version). Our
-[issue template](https://github.com/explosion/spaCy/issues/new) helps you
+[issue templates](https://github.com/explosion/spaCy/issues/new/choose) help you
 remember the most important details to include. If you've discovered a bug, you
 can also submit a [regression test](#fixing-bugs) straight away. When you're
 opening an issue to report the bug, simply refer to your pull request in the

requirements.txt

@@ -3,7 +3,7 @@ spacy-legacy>=3.0.11,<3.1.0
 spacy-loggers>=1.0.0,<2.0.0
 cymem>=2.0.2,<2.1.0
 preshed>=3.0.2,<3.1.0
-thinc>=8.2.2,<8.3.0
+thinc>=8.3.0,<8.4.0
 ml_datasets>=0.2.0,<0.3.0
 murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.2.0

setup.cfg

@@ -17,8 +17,6 @@ classifiers =
     Operating System :: Microsoft :: Windows
     Programming Language :: Cython
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.7
-    Programming Language :: Python :: 3.8
     Programming Language :: Python :: 3.9
     Programming Language :: Python :: 3.10
     Programming Language :: Python :: 3.11
@@ -31,7 +29,7 @@ project_urls =
 [options]
 zip_safe = false
 include_package_data = true
-python_requires = >=3.7
+python_requires = >=3.9
 # NOTE: This section is superseded by pyproject.toml and will be removed in
 # spaCy v4
 setup_requires =
@@ -116,7 +114,7 @@ cuda12x =
 cuda-autodetect =
     cupy-wheel>=11.0.0,<13.0.0
 apple =
-    thinc-apple-ops>=0.1.0.dev0,<1.0.0
+    thinc-apple-ops>=1.0.0,<2.0.0
 # Language tokenizers with external dependencies
 ja =
     sudachipy>=0.5.2,!=0.6.1

spacy/about.py

@@ -1,5 +1,5 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.8.0"
+__version__ = "3.8.2"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/lang/hr/lemma_lookup_license.txt

@@ -1,5 +1,5 @@
 The list of Croatian lemmas was extracted from the reldi-tagger repository (https://github.com/clarinsi/reldi-tagger).
-Reldi-tagger is licesned under the Apache 2.0 licence.
+Reldi-tagger is licensed under the Apache 2.0 licence.
 
 @InProceedings{ljubesic16-new,
   author = {Nikola Ljubešić and Filip Klubička and Željko Agić and Ivo-Pavao Jazbec},
@@ -12,4 +12,4 @@ Reldi-tagger is licesned under the Apache 2.0 licence.
   publisher = {European Language Resources Association (ELRA)},
   address = {Paris, France},
   isbn = {978-2-9517408-9-1}
- }
+ }

spacy/language.py

@@ -9,7 +9,6 @@
 from copy import deepcopy
 from dataclasses import dataclass
 from itertools import chain, cycle
-import numpy
 from pathlib import Path
 from timeit import default_timer as timer
 from typing import (
@@ -31,6 +30,7 @@
     overload,
 )
 
+import numpy
 import srsly
 from cymem.cymem import Pool
 from thinc.api import Config, CupyOps, Optimizer, get_current_ops
@@ -2143,7 +2143,9 @@ def to_disk(
         serializers["tokenizer"] = lambda p: self.tokenizer.to_disk(  # type: ignore[union-attr]
             p, exclude=["vocab"]
         )
-        serializers["meta.json"] = lambda p: srsly.write_json(p, _replace_numpy_floats(self.meta))
+        serializers["meta.json"] = lambda p: srsly.write_json(
+            p, _replace_numpy_floats(self.meta)
+        )
         serializers["config.cfg"] = lambda p: self.config.to_disk(p)
         for name, proc in self._components:
             if name in exclude:
@@ -2257,7 +2259,9 @@ def to_bytes(self, *, exclude: Iterable[str] = SimpleFrozenList()) -> bytes:
         serializers: Dict[str, Callable[[], bytes]] = {}
         serializers["vocab"] = lambda: self.vocab.to_bytes(exclude=exclude)
         serializers["tokenizer"] = lambda: self.tokenizer.to_bytes(exclude=["vocab"])  # type: ignore[union-attr]
-        serializers["meta.json"] = lambda: srsly.json_dumps(_replace_numpy_floats(self.meta))
+        serializers["meta.json"] = lambda: srsly.json_dumps(
+            _replace_numpy_floats(self.meta)
+        )
         serializers["config.cfg"] = lambda: self.config.to_bytes()
         for name, proc in self._components:
             if name in exclude:
@@ -2309,7 +2313,9 @@ def deserialize_meta(b):
 
 
 def _replace_numpy_floats(meta_dict: dict) -> dict:
-    return convert_recursive(lambda v: isinstance(v, numpy.floating), lambda v: float(v), dict(meta_dict))
+    return convert_recursive(
+        lambda v: isinstance(v, numpy.floating), lambda v: float(v), dict(meta_dict)
+    )
 
 
 @dataclass

spacy/tests/training/test_pretraining.py renamed to spacy/tests/training/test_pretraining.py.disabled

@@ -1597,7 +1597,7 @@ The name of the model to be used has to be passed in via the `name` attribute.
 
 | Argument | Description                                                                                                                                                           |
 | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `name`   | The name of a mdodel supported by LangChain for this API. ~~str~~                                                                                                     |
+| `name`   | The name of a model supported by LangChain for this API. ~~str~~                                                                                                     |
 | `config` | Configuration passed on to the LangChain model. Defaults to `{}`. ~~Dict[Any, Any]~~                                                                                  |
 | `query`  | Function that executes the prompts. If `None`, defaults to `spacy.CallLangChain.v1`. ~~Optional[Callable[["langchain.llms.BaseLLM", Iterable[Any]], Iterable[Any]]]~~ |
 

website/docs/api/large-language-models.mdx

@@ -720,7 +720,7 @@ matches = matcher(doc)
 
 # Serve visualization of sentences containing match with displaCy
 # set manual=True to make displaCy render straight from a dictionary
-# (if you're not running the code within a Jupyer environment, you can
+# (if you're not running the code within a Jupyter environment, you can
 # use displacy.serve instead)
 displacy.render(matched_sents, style="ent", manual=True)
 ```