We're not really using spaCy but it was still a dependency

Author: nonprofittechy

formfyxer/lit_explorer.py

@@ -373,10 +373,8 @@ def vectorize(text: Union[List[str], str], tools_token: Optional[str] = None):
     Args:
       text: a string of multiple words to vectorize
       tools_token: the token to tools.suffolklitlab.org, used for micro-service
-          to reduce the amount of memory you need on your machine. If
-          not passed, you need to have `en_core_web_lg` installed. NOTE: this 
-          last bit is nolonger correct, you have to use the micor-service
-          as we have had to remove SpaCY due to a breaking change
+          to reduce the amount of memory you need on your machine. This token
+          is required as we have removed SpaCY dependencies due to breaking changes.
     """
     if tools_token:
         headers = {

formfyxer/requirements.txt

@@ -15,11 +15,8 @@ reportlab
 requests
 ocrmypdf
 scikit-learn
-spacy
 textstat
 transformers
 types-requests
 types-PyYAML
-en-core-web-lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.5.0/en_core_web_lg-3.5.0-py3-none-any.whl
-typer>=0.4.1,<0.5.0
 python-docx

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools>=40.0.0", "pip", "spacy"]
+requires = ["setuptools>=40.0.0", "pip"]
 build-backend = "setuptools.build_meta"
 
 [tool.black]
@@ -26,18 +26,6 @@ ignore_missing_imports = true
 module="networkx.*"
 ignore_missing_imports = true
 
-[[tool.mypy.overrides]]
-module="en_core_web_lg.*"
-ignore_missing_imports=true
-
-[[tool.mypy.overrides]]
-module="en_core_web_md.*"
-ignore_missing_imports=true
-
-[[tool.mypy.overrides]]
-module="en_core_web_sm.*"
-ignore_missing_imports=true
-
 [[tool.mypy.overrides]]
 module="boxdetect.*"
 ignore_missing_imports=true

setup.py

@@ -4,16 +4,6 @@
 with open("README.md", "r", encoding="utf-8") as fh:
     long_description = fh.read()
 
-# We can't simply include this as an install_requires, because pypi won't allow
-# projects with github dependencies to be hosted there.
-#class InstallSpacyModelCommand(install):
-#    def run(self):
-#        install.run(self)
-#        import spacy
-#        print("Downloading word2vec model en_core_web_sm")
-#        spacy.cli.download('en_core_web_sm')
-
-
 setuptools.setup(
     name='formfyxer',
     version='0.3.0a3',
@@ -28,15 +18,11 @@
     },
     license='MIT',
     packages=['formfyxer'],
-    install_requires=['spacy', 'pdfminer.six', 'pandas', 'pikepdf',
+    install_requires=['pdfminer.six', 'pandas', 'pikepdf',
         'textstat', 'requests', 'numpy', 'scikit-learn', 'networkx', 'joblib',
         'nltk', 'boxdetect', 'pdf2image', 'reportlab>=3.6.13', 'pdfminer.six',
         'opencv-python', 'ocrmypdf', 'eyecite', 'passivepy>=0.2.16', 'sigfig',
-        'typer>=0.4.1,<0.5.0', # typer pre 0.4.1 was broken by click 8.1.0: https://github.com/explosion/spaCy/issues/10564
         'openai', 'python-dotenv', 'python-docx', 'tiktoken', 'transformers' 
     ],
-    #cmdclass={
-    #  'install': InstallSpacyModelCommand,
-    #},
     include_package_data = True
 )