removed spacy models from pyproject.toml as they cannot be used as de…

…pendencies
microsoft · Dec 1, 2024 · 281c159 · 281c159
1 parent 4a2d95d
commit 281c159
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -44,9 +44,15 @@ To install the package:
 pip install poetry
 poetry install --with=dev
 
+# Download tge spaCy pipeline used for tokenization
+poetry run python -m spacy download en_core_web_sm
+
 # To install with all additional NER dependencies (e.g. Flair, Stanza), run:
 # poetry install --with='ner,dev'
 
+# To use the default Presidio configuration, a spaCy model is required:
+poetry run python -m spacy download en_core_web_lg
+
 # Verify installation
 pytest
 ```

diff --git a/pyproject.toml b/pyproject.toml
@@ -22,8 +22,6 @@ xmltodict = "^0.12.0"
 python-dotenv = "^1.0.0"
 plotly= "^5.24.0"
 azure-ai-textanalytics = "^5.3.0"
-en_core_web_sm = {url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0.tar.gz"}
-en_core_web_lg = {url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.8.0/en_core_web_lg-3.8.0.tar.gz"}
 
 # optional dependencies for the different NLP approaches
 [tool.poetry.group.ner]