Packaging update (#22)

* Update __init__.py

* Update pyproject.toml

* fmt with black

* add poetry

* update checkout

* update poetry lock

* update: release pipeline

* add setup

* rm setup

* rm 3.10

* update: release pipeline

.github/workflows/codeql-analysis.yml

@@ -35,7 +35,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/test_release.yml

@@ -20,21 +20,22 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python: ['3.7','3.8','3.9','3.10']
+        python: ['3.8','3.9','3.10']
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Python 3.x
       uses: actions/setup-python@v2
       with:
         python-version: ${{ matrix.python }}
-        cache: 'pip'
-        cache-dependency-path: '**/requirements*.txt'
 
     - name: Install dependencies
       run: |
-        pip install -r requirements_dev.txt
-        pip install -e .[sentence_transformers]
+        pip install poetry==1.8.3
+        poetry config virtualenvs.create false
+        poetry check --lock
+        poetry install --extras sentence_transformers --with test
+        
     
     - name: Lint with flake8
       run: |
@@ -54,10 +55,10 @@ jobs:
 
     - name: Generate Report
       run: |
-        coverage run -m --source=./hf_hub_ctranslate2 pytest tests 
+        coverage run -m --source=hf_hub_ctranslate2 pytest tests 
         coverage xml
     - name: Upload coverage to Codecov for python 3.8
-      if: ${{ matrix.python == '3.8' }}
+      if: ${{ matrix.python == '3.10' }}
       uses: codecov/codecov-action@v2
 
   deploy_docs:
@@ -67,28 +68,22 @@ jobs:
     # only run if pytest successfull
     steps:
     - name: Checkout current branch
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
       with:
         path: 'branch-dir'
 
     - name: Checkout gh-pages branch
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
       with:
         ref: 'gh-pages'
         path: 'gh-pages-dir'
 
-    - name: Set up Python 3.8
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.8
-        cache: 'pip'
-        cache-dependency-path: '**/requirements*.txt'
-
     - name: Install dependencies from current branch
       run: |
         cd branch-dir
-        pip install -r requirements_dev.txt
-        pip install -e .[sentence_transformers]
+        pip install poetry==1.8.3
+        poetry config virtualenvs.create false
+        poetry install --extras sentence_transformers --with test
     - name: create shinx docs from current branch
       # create shpinx api autodocs of opensentiment and move them to docs
       # makefile: make html build the the docs/_build/html/
@@ -131,11 +126,11 @@ jobs:
     permissions:
       id-token: write
     steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python 3.8
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.10
       uses: actions/setup-python@v2
       with:
-        python-version: 3.8
+        python-version: 3.10
 
     - name: Install pypa/build
       run: |

hf_hub_ctranslate2/__init__.py

@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
 """Compatability between Huggingface and Ctranslate2."""
 # __all__ = ["__version__", "TranslatorCT2fromHfHub", "GeneratorCT2fromHfHub", "MultiLingualTranslatorCT2fromHfHub"]
+import importlib.metadata
+import os
 from hf_hub_ctranslate2.translate import (
     TranslatorCT2fromHfHub,
     GeneratorCT2fromHfHub,
@@ -9,4 +11,4 @@
 )
 from hf_hub_ctranslate2.ct2_sentence_transformers import CT2SentenceTransformer
 
-__version__ = "2.13.0"
+__version__ = importlib.metadata.version("hf_hub_ctranslate2")

pyproject.toml

@@ -1,6 +1,36 @@
+[tool.poetry]
+name = "hf_hub_ctranslate2"
+version = "2.13.0"
+description = "Connecting Transfromers on HuggingfaceHub with Ctranslate2."
+authors = ["michaelfeil <mail at michaelfeil.eu>"]
+license = "MIT"
+readme = "README.md"
+packages = [{include = "hf_hub_ctranslate2"}]
+
+[tool.poetry.dependencies]
+python = ">=3.8,<3.13"
+numpy = "*"
+ctranslate2 = ">=3.16.0"
+transformers = ">=4.28.0"
+huggingface-hub = "*"
+sentence_transformers = {version="2.2.2", optional=true}
+
+[tool.poetry.group.test.dependencies]
+pytest= "6.2.5"
+pytest-ordering = "0.6"
+Sphinx = "5.*"
+sphinx-rtd-theme = "1.0.0"
+coverage = "6.2"
+flake8 = "*"
+pre-commit = "*"
+myst-parser = {version="1.*",extras=["sphinx"]}
+mkdocs = "*"
+sentencepiece = "*"
+typing_extensions = "*"
+
+[tool.poetry.extras]
+sentence_transformers=["sentence_transformers"]
+
 [build-system]
-requires = [
-    "setuptools>=60",
-    "wheel"
-]
-build-backend = "setuptools.build_meta"
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/test_translate.py

@@ -7,6 +7,7 @@
 
 from hf_hub_ctranslate2.util import utils as _utils
 from transformers import AutoTokenizer
+import numpy as np
 
 
 def test_encoder(model_name="michaelfeil/ct2fast-e5-small-v2"):
@@ -19,7 +20,6 @@ def test_encoder(model_name="michaelfeil/ct2fast-e5-small-v2"):
     )["pooler_output"]
     assert len(embeddings) == 3
     assert len(embeddings[0]) == len(embeddings[1])
-    import numpy as np
 
     assert isinstance(embeddings, np.ndarray)
     embeddings_norm = embeddings / (embeddings**2).sum(axis=1, keepdims=True) ** 0.5