From 281c1594be72173afaa5a2dc696a461eaf0c2840 Mon Sep 17 00:00:00 2001
From: Omri Mendels <omri374@users.noreply.github.com>
Date: Sun, 1 Dec 2024 13:59:06 +0200
Subject: [PATCH] removed spacy models from pyproject.toml as they cannot be
 used as dependencies

---
 README.md      | 6 ++++++
 pyproject.toml | 2 --
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index fe51663..bd74887 100644
--- 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
index f6f44b7..3faf974 100644
--- 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]