beenull/mwmbl
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Merge pull request #83 from omasanori/spacy-deps-rework

Browse source 
Rework installation of spaCy models for clarity
This commit is contained in:
Daoud Clarke 2022-12-27 10:20:52 +00:00 committed by GitHub
parent d85067ec09 71187a3938
commit f3f3831a97
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 5 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
Dockerfile
View file

@ -26,8 +26,11 @@ COPY mwmbl /app/mwmbl
# Use pip to install the mwmbl python package
# PEP 518, PEP 517 and others have allowed for a standardized python packaging API, which allows
# pip to be able to install poetry packages.
RUN /venv/bin/pip install pip --upgrade && \
/venv/bin/pip install .
# en-core-web-sm requires a compatible version of spacy
RUN /venv/bin/pip install pip wheel --upgrade && \
/venv/bin/pip install . && \
/venv/bin/python -m spacy download en_core_web_sm-3.2.0 --direct && \
/venv/bin/python -m spacy validate
FROM base as final

4
pyproject.toml
View file

@ -31,9 +31,6 @@ langdetect = {version= "==1.0.9", optional = true}
pyarrow = {version= "==6.0.0", optional = true}
pyspark = {version= "==3.2.0", optional = true}
Levenshtein = {version= "==0.16.0", optional = true}
# en-core-web-sm requires a compatible version of spacy
en-core-web-sm = {url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0.tar.gz"}
[tool.poetry.extras]
indexer = [
@ -47,7 +44,6 @@ indexer = [
"pyarrow",
"pyspark",
"Levenshtein",
# en-core-web-sm requires a compatible version of spacy
]
[tool.poetry.dev-dependencies]