Use mypy

Author: Askir

.github/workflows/mypy.yaml

@@ -0,0 +1,24 @@
+name: Type Checking
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  mypy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Install uv
+      run: pip install uv
+    - name: Create venv
+      run: uv venv
+    - name: Install dependencies
+      run: |
+        uv sync
+    - name: Run Mypy
+      run: uv run mypy .

pyproject.toml

@@ -23,18 +23,6 @@ dependencies = [
     "numpy>=1,<2",
 ]
 
-[project.optional-dependencies]
-dev = [
-    "ruff>=0.6.9",
-    "pyright>=1.1.384",
-    "pytest>=8.3.3",
-    "langchain>=0.3.3",
-    "langchain-openai>=0.2.2",
-    "langchain-community>=0.3.2",
-    "pandas>=2.2.3",
-    "pytest-asyncio>=0.24.0",
-]
-
 [project.urls]
 repository = "https://github.com/timescale/python-vector"
 documentation = "https://timescale.github.io/python-vector"
@@ -51,36 +39,46 @@ addopts = [
     "--import-mode=importlib",
 ]
 
-[tool.pyright]
-typeCheckingMode = "strict"
-reportImplicitOverride = true
-exclude = [
-    "**/.bzr",
-    "**/.direnv",
-    "**/.eggs",
-    "**/.git",
-    "**/.git-rewrite",
-    "**/.hg",
-    "**/.ipynb_checkpoints",
-    "**/.mypy_cache",
-    "**/.nox",
-    "**/.pants.d",
-    "**/.pyenv",
-    "**/.pytest_cache",
-    "**/.pytype",
-    "**/.ruff_cache",
-    "**/.svn",
-    "**/.tox",
-    "**/.venv",
-    "**/.vscode",
-    "**/__pypackages__",
-    "**/_build",
-    "**/buck-out",
-    "**/dist",
-    "**/node_modules",
-    "**/site-packages",
-    "**/venv",
-]
+
+[tool.mypy]
+strict = true
+ignore_missing_imports = true
+namespace_packages = true
+
+
+#[tool.pyright]
+#reportMissingTypeStubs = false
+#exclude = [
+#    "**/.bzr",
+#    "**/.direnv",
+#    "**/.eggs",
+#    "**/.git",
+#    "**/.git-rewrite",
+#    "**/.hg",
+#    "**/.ipynb_checkpoints",
+#    "**/.mypy_cache",
+#    "**/.nox",
+#    "**/.pants.d",
+#    "**/.pyenv",
+#    "**/.pytest_cache",
+#    "**/.pytype",
+#    "**/.ruff_cache",
+#    "**/.svn",
+#    "**/.tox",
+#    "**/.venv",
+#    "**/.vscode",
+#    "**/__pypackages__",
+#    "**/_build",
+#    "**/buck-out",
+#    "**/dist",
+#    "**/node_modules",
+#    "**/site-packages",
+#    "**/venv",
+#]
+
+#[[tool.pyright.overrides]]
+#source = ["**/*.py"]
+#ignore = ["asyncpg", "pgvector.psycopg2", "psycopg2", "asyncpg.*"]
 
 [tool.ruff]
 line-length = 120
@@ -137,4 +135,18 @@ select = [
     "W291",
     "PIE",
     "Q"
-]
+]
+
+[tool.uv]
+dev-dependencies = [
+    "mypy>=1.12.0",
+    "types-psycopg2>=2.9.21.20240819",
+    "ruff>=0.6.9",
+    "pyright>=1.1.384",
+    "pytest>=8.3.3",
+    "langchain>=0.3.3",
+    "langchain-openai>=0.2.2",
+    "langchain-community>=0.3.2",
+    "pandas>=2.2.3",
+    "pytest-asyncio>=0.24.0",
+]

tests/async_client_test.py

@@ -306,7 +306,7 @@ async def test_vector(service_url: str, schema: str) -> None:
     assert not await vec.table_is_empty()
 
     # check all the possible ways to specify a date range
-    async def search_date(start_date, end_date, expected):
+    async def search_date(start_date: datetime | str | None, end_date: datetime | str | None, expected: int) -> None:
         # using uuid_time_filter
         rec = await vec.search(
             [1.0, 2.0],

tests/pg_vectorizer_test.py

@@ -1,4 +1,5 @@
 from datetime import timedelta
+from typing import Any
 
 import psycopg2
 import pytest
@@ -11,7 +12,7 @@
 from timescale_vector.pgvectorizer import Vectorize
 
 
-def get_document(blog):
+def get_document(blog: dict[str, Any]) -> list[Document]:
     text_splitter = CharacterTextSplitter(
         chunk_size=1000,
         chunk_overlap=200,
@@ -56,7 +57,7 @@ def test_pg_vectorizer(service_url: str) -> None:
             VALUES ('first', 'mat', 'first_post', 'personal', '2021-01-01');
         """)
 
-    def embed_and_write(blog_instances, vectorizer):
+    def embed_and_write(blog_instances: list[Any], vectorizer: Vectorize) -> None:
         TABLE_NAME = vectorizer.table_name_unquoted + "_embedding"
         embedding = OpenAIEmbeddings()
         vector_store = TimescaleVector(

tests/sync_client_test.py

@@ -136,15 +136,15 @@ def test_sync_client(service_url: str, schema: str) -> None:
 
     rec = vec.search([1.0, 2.0], filter={"key_1": "val_1", "key_2": "val_2"})
     assert rec[0][SEARCH_RESULT_CONTENTS_IDX] == "the brown fox"
-    assert rec[0]["contents"] == "the brown fox"
+    assert rec[0]["contents"] == "the brown fox"  # type: ignore
     assert rec[0][SEARCH_RESULT_METADATA_IDX] == {
         "key_1": "val_1",
         "key_2": "val_2",
     }
-    assert rec[0]["metadata"] == {"key_1": "val_1", "key_2": "val_2"}
+    assert rec[0]["metadata"] == {"key_1": "val_1", "key_2": "val_2"}  # type: ignore
     assert isinstance(rec[0][SEARCH_RESULT_METADATA_IDX], dict)
     assert rec[0][SEARCH_RESULT_DISTANCE_IDX] == 0.0009438353921149556
-    assert rec[0]["distance"] == 0.0009438353921149556
+    assert rec[0]["distance"] == 0.0009438353921149556  # type: ignore
 
     rec = vec.search([1.0, 2.0], limit=4, predicates=Predicates("key", "==", "val2"))
     assert len(rec) == 1
@@ -218,7 +218,7 @@ def test_sync_client(service_url: str, schema: str) -> None:
         ]
     )
 
-    def search_date(start_date, end_date, expected):
+    def search_date(start_date: datetime | str | None, end_date: datetime | str | None, expected: int) -> None:
         # using uuid_time_filter
         rec = vec.search(
             [1.0, 2.0],