add GA to publish to pypi

.github/workflows/publish.yml

@@ -0,0 +1,46 @@
+# ref: https://johnfraney.ca/blog/how-to-publish-a-python-package-with-poetry-and-github-actions/
+name: Upload Python Package to PyPI when a Release is Created
+
+on:
+  release:
+    types: [created]
+
+permissions:
+  contents: read
+
+jobs:
+  pypi-publish:
+    name: Publish release to PyPI
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/spacy-lancedb-linker
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install Poetry
+        run: |
+          curl -sSL https://install.python-poetry.org | python - -y
+
+      - name: Update PATH
+        run: echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Update Poetry configuration
+        run: poetry config virtualenvs.create false
+
+      - name: Install dependencies
+        run: poetry install --sync --no-interaction
+
+      - name: Package project
+        run: poetry build
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

README.md

@@ -4,32 +4,71 @@
 
 ## Installation
 
-```python
-poetry install
+```sh
+pip install spacy-lancedb-linker
 ```
 
 ## Usage
 
 ```python
-poetry shell
-poetry run ...
-```
+import spacy
 
-## test
+from spacy_lancedb_linker.kb import AnnKnowledgeBase
+from spacy_lancedb_linker.linker import AnnLinker  # noqa
+from spacy_lancedb_linker.types import Alias, Entity
 
-```python
-poetry run pytest
-```
+nlp = spacy.load("en_core_web_md")
+kb = AnnKnowledgeBase(uri="data/sample-lancedb")
+kb.add_entities(
+    [
+        Entity(**entity)
+        for entity in [
+            {
+                "entity_id": "a3",
+                "name": "Natural language processing",
+                "description": "Natural language processing (NLP) is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data.",
+            },
+            {
+                "entity_id": "a4",
+                "name": "Neuro-linguistic programming",
+                "description": "Neuro-linguistic programming (NLP) is a pseudoscientific approach to communication, personal development, and psychotherapy created by Richard Bandler and John Grinder in California, United States in the 1970s.",
+            },
+        ]
+    ]
+)
+kb.add_aliases(
+    [
+        Alias(**alias)
+        for alias in [
+            {"alias": "NLP", "entities": ["a3", "a4"], "probabilities": [0.5, 0.5]},
+            {
+                "alias": "Natural language processing",
+                "entities": ["a3"],
+                "probabilities": [1.0],
+            },
+            {
+                "alias": "Neuro-linguistic programming",
+                "entities": ["a4"],
+                "probabilities": [1.0],
+            },
+        ]
+    ]
+)
 
-## TODO
+ann_linker = nlp.add_pipe("ann_linker", last=True)
+ann_linker.set_kb(kb)
 
-- setup trusted publisher github action https://medium.com/@blackary/publishing-a-python-package-from-github-to-pypi-in-2024-a6fb8635d45d
+doc = nlp("NLP is a subset of machine learn.")
 
-Other
+print(doc.ents[0].kb_id_)
+print(doc.ents[0]._.alias_candidates)
+print(doc.ents[0]._.kb_candidates)
+```
+
+## Test
 
-- docs?
-- more Github actions?
-- add docker https://matt.sh/python-project-structure-2024#_living-with-pyproject.toml
-- test coverage
-- test across python versions
-- use collections, itertools, more-itertools, boltons, sortedcontainers, diskcache, peewee, httpx, loguru, orjson
+```sh
+poetry install
+poetry shell
+poetry run pytest
+```

pyproject.toml

@@ -9,7 +9,7 @@ readme = "README.md"
 homepage = "https://guitton.co/"
 repository = "https://github.com/louisguitton/spacy-lancedb-linker"
 documentation = "https://guitton.co/"
-keywords = ["spacy", "entity-linking", "ann", "lancedb"]
+keywords = ["spacy", "spacy-pipeline", "entity-linking", "ann", "lancedb"]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Developers",