switch from spacy to stanza for compatibility

Dockerfile

@@ -9,16 +9,18 @@ COPY ./new_requirements.txt /code/new_requirements.txt
 RUN pip install --no-cache-dir --upgrade -r /code/new_requirements.txt
 
 # Install spaCy model
-RUN python -m spacy download en_core_web_sm
+# RUN python -m spacy download en_core_web_sm
 
 # Patch SpaCy to use Pydantic v1 in case v2 is installed
-RUN sed -i 's/from pydantic import ConstrainedStr/from pydantic.v1 import ConstrainedStr/' \
-    /usr/local/lib/python3.10/site-packages/spacy/schemas.py
+# RUN sed -i 's/from pydantic import ConstrainedStr/from pydantic.v1 import ConstrainedStr/' \
+#     /usr/local/lib/python3.10/site-packages/spacy/schemas.py
 
 
 # Install Pydantic v1 and SpaCy explicitly to prevent version conflicts
 # RUN pip install pydantic==1.10.12 spacy==3.5.3
-RUN pip install pydantic==1.10.12
+# RUN pip install pydantic==1.10.12
+
+RUN pip install stanza==1.9.2
 
 # Copy the local en_core_web_sm-3.0.0.tar.gz file into the container
 # COPY ./en_core_web_sm-3.0.0.tar.gz /models/en_core_web_sm-3.0.0.tar.gz

requirements.txt

@@ -1,195 +0,0 @@
-aiohappyeyeballs==2.4.0
-aiohttp==3.10.5
-aiosignal==1.3.1
-annotated-types==0.7.0
-anyio==4.4.0
-appnope==0.1.4
-argon2-cffi==23.1.0
-argon2-cffi-bindings==21.2.0
-arrow==1.3.0
-asttokens==2.4.1
-async-lru==2.0.4
-attrs==24.2.0
-babel==2.16.0
-beautifulsoup4==4.12.3
-bleach==6.1.0
-blinker==1.8.2
-blis==0.7.11
-catalogue==2.0.10
-certifi==2024.8.30
-cffi==1.17.0
-charset-normalizer==3.3.2
-click==8.1.7
-cloudpathlib==0.19.0
-comm==0.2.2
-confection==0.1.5
-contourpy==1.3.0
-cycler==0.12.1
-cymem==2.0.8
-datasets==2.21.0
-debugpy==1.8.5
-decorator==5.1.1
-defusedxml==0.7.1
-dill==0.3.8
-executing==2.0.1
-fastai==2.7.17
-fastbook==0.0.29
-fastcore==1.7.3
-fastdownload==0.0.7
-fastjsonschema==2.20.0
-fastprogress==1.0.3
-filelock==3.15.4
-Flask==3.0.3
-fonttools==4.53.1
-fqdn==1.5.1
-frozenlist==1.4.1
-fsspec==2024.6.1
-graphviz==0.20.3
-h11==0.14.0
-httpcore==1.0.5
-httpx==0.27.2
-huggingface-hub==0.24.6
-idna==3.8
-iniconfig==2.0.0
-ipykernel==6.29.5
-ipython==8.27.0
-ipython-genutils==0.2.0
-ipywidgets==7.8.3
-isoduration==20.11.0
-itsdangerous==2.2.0
-jedi==0.19.1
-Jinja2==3.1.4
-joblib==1.4.2
-json5==0.9.25
-jsonpointer==3.0.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-jupyter-events==0.10.0
-jupyter-lsp==2.2.5
-jupyter_client==8.6.2
-jupyter_core==5.7.2
-jupyter_server==2.14.2
-jupyter_server_terminals==0.5.3
-jupyterlab==4.2.5
-jupyterlab_pygments==0.3.0
-jupyterlab_server==2.27.3
-jupyterlab_widgets==1.1.9
-kaggle==1.6.17
-kiwisolver==1.4.5
-langcodes==3.4.0
-language_data==1.2.0
-marisa-trie==1.2.0
-markdown-it-py==3.0.0
-MarkupSafe==2.1.5
-matplotlib==3.9.2
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-mistune==3.0.2
-mpmath==1.3.0
-multidict==6.0.5
-multiprocess==0.70.16
-murmurhash==1.0.10
-nbclient==0.10.0
-nbconvert==7.16.4
-nbformat==5.10.4
-nest-asyncio==1.6.0
-networkx==3.3
-nltk==3.8.1
-notebook==7.2.2
-notebook_shim==0.2.4
-numpy==1.26.4
-overrides==7.7.0
-packaging==24.1
-pandas==2.2.2
-pandocfilters==1.5.1
-parso==0.8.4
-pathlib==1.0.1
-pexpect==4.9.0
-pillow==10.4.0
-platformdirs==4.2.2
-pluggy==1.5.0
-preshed==3.0.9
-prometheus_client==0.20.0
-prompt_toolkit==3.0.47
-psutil==6.0.0
-ptyprocess==0.7.0
-pure_eval==0.2.3
-pyarrow==17.0.0
-pycparser==2.22
-pydantic==1.7.4
-pydantic_core==2.20.1
-Pygments==2.18.0
-pyparsing==3.1.4
-pytest==8.3.3
-python-dateutil==2.9.0.post0
-python-json-logger==2.0.7
-python-slugify==8.0.4
-pytz==2024.1
-PyYAML==6.0.2
-pyzmq==26.2.0
-referencing==0.35.1
-regex==2024.7.24
-requests==2.32.3
-rfc3339-validator==0.1.4
-rfc3986-validator==0.1.1
-rich==13.8.0
-rpds-py==0.20.0
-safetensors==0.4.4
-scikit-learn==1.5.1
-scipy==1.14.1
-Send2Trash==1.8.3
-sentencepiece==0.2.0
-setuptools==75.1.0
-shellingham==1.5.4
-six==1.16.0
-smart-open==5.2.1
-sniffio==1.3.1
-soupsieve==2.6
-# spacy==3.5.0
-# spacy==3.7.6
-spacy==3.5.3
-spacy-lookups-data==1.0.0
-spacy-legacy==3.0.12
-spacy-loggers==1.0.5
-srsly==2.4.8
-stack-data==0.6.3
-sympy==1.13.2
-terminado==0.18.1
-text-unidecode==1.3
-thinc==8.1.8
-threadpoolctl==3.5.0
-tinycss2==1.3.0
-tokenizers==0.19.1
-torch==2.4.0
-torchaudio==2.4.0
-torchvision==0.19.0
-tornado==6.4.1
-tqdm==4.66.5
-traitlets==5.14.3
-transformers==4.44.2
-# typer==0.3.0
-# typer==0.9.0
-typer==0.*
-types-python-dateutil==2.9.0.20240821
-typing_extensions==4.12.2
-tzdata==2024.1
-uri-template==1.3.0
-urllib3==2.2.2
-wasabi==1.1.3
-wcwidth==0.2.13
-weasel==0.4.1
-webcolors==24.8.0
-webencodings==0.5.1
-websocket-client==1.8.0
-Werkzeug==3.0.3
-wget==3.2
-wheel==0.44.0
-widgetsnbextension==3.6.8
-wrapt==1.16.0
-xxhash==3.5.0
-yarl==1.9.6
-# spacy[transformers]
-# https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz
-# spacy[en]==3.2.0
-# en-core-web-sm==3.5.0
-https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl