datachain 0.34.6__tar.gz → 0.35.0__tar.gz

{datachain-0.34.6 → datachain-0.35.0}/.github/workflows/tests.yml

@@ -23,10 +23,10 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.event.pull_request.head.sha || github.ref }}
 
-      - name: Set up Python 3.9
+      - name: Set up Python 3.10
         uses: actions/setup-python@v6
         with:
-          python-version: '3.9'
+          python-version: '3.10'
 
       - name: Setup uv
         uses: astral-sh/setup-uv@v6
@@ -60,14 +60,14 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest-8-cores]
-        pyv: ['3.9', '3.10', '3.11', '3.12', '3.13']
+        pyv: ['3.10', '3.11', '3.12', '3.13']
         include:
           - os: macos-latest
-            pyv: '3.9'
+            pyv: '3.10'
           - os: macos-latest
             pyv: '3.13'
           - os: windows-latest
-            pyv: '3.9'
+            pyv: '3.10'
           - os: windows-latest
             pyv: '3.13'
 
@@ -166,15 +166,15 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest, windows-latest]
-        pyv: ['3.9', '3.13']
+        pyv: ['3.10', '3.13']
         group: ['get_started', 'computer_vision', 'multimodal']
         exclude:
-          - {os: ubuntu-latest, pyv: '3.9', group: 'multimodal'}
+          - {os: ubuntu-latest, pyv: '3.10', group: 'multimodal'}
           - {os: ubuntu-latest, pyv: '3.13', group: 'multimodal'}
         include:
           # HF runs against actual API - thus run it only once
           - {os: ubuntu-latest, pyv: "3.13", group: llm_and_nlp}
-          - {os: ubuntu-latest-4-cores, pyv: "3.9", group: multimodal}
+          - {os: ubuntu-latest-4-cores, pyv: "3.10", group: multimodal}
           - {os: ubuntu-latest-4-cores, pyv: "3.13", group: multimodal}
 
     steps:

{datachain-0.34.6 → datachain-0.35.0}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.13.2'
+    rev: 'v0.13.3'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.34.6 → datachain-0.35.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.34.6
+Version: 0.35.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -8,13 +8,12 @@ Project-URL: Documentation, https://datachain.dvc.ai
 Project-URL: Issues, https://github.com/iterative/datachain/issues
 Project-URL: Source, https://github.com/iterative/datachain
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Development Status :: 2 - Pre-Alpha
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: pyyaml

{datachain-0.34.6 → datachain-0.35.0}/docs/commands/job/run.md

@@ -35,7 +35,7 @@ This command runs a job in Studio using the specified query file. You can config
 * `--credentials-name CREDENTIALS_NAME` - Name of the credentials to use for the job
 * `--workers WORKERS` - Number of workers for the job
 * `--files FILES` - Additional files to include in the job
-* `--python-version PYTHON_VERSION` - Python version for the job (e.g., 3.9, 3.10, 3.11)
+* `--python-version PYTHON_VERSION` - Python version for the job (e.g., 3.10, 3.11, 3.12, 3.13)
 * `--repository REPOSITORY` - Repository URL to clone before running the job
 * `--req-file REQ_FILE` - Python requirements file
 * `--req REQ` - Python package requirements

{datachain-0.34.6 → datachain-0.35.0}/docs/guide/namespaces.md

@@ -168,7 +168,7 @@ Use `delete_namespace` to remove an empty namespace or an empty project within a
 ### Signature
 
 ```python
-def delete_namespace(name: str, session: Optional[Session]) -> None:
+def delete_namespace(name: str, session: Session | None) -> None:
 ```
 
 - **`<namespace>`** — deletes the namespace (must contain no projects or datasets).

{datachain-0.34.6 → datachain-0.35.0}/examples/get_started/json-csv-reader.py

@@ -1,5 +1,4 @@
 import os
-from typing import Optional
 
 import datachain as dc
 from datachain import DataModel
@@ -15,10 +14,10 @@ class LicenseModel(DataModel):
 
 # Sample model for static CSV model
 class ChatDialog(DataModel):
-    id: Optional[int] = None
-    count: Optional[int] = None
-    sender: Optional[str] = None
-    text: Optional[str] = None
+    id: int | None = None
+    count: int | None = None
+    sender: str | None = None
+    text: str | None = None
 
 
 def main():

{datachain-0.34.6 → datachain-0.35.0}/examples/get_started/nested_datamodel.py

@@ -7,8 +7,6 @@ The example keeps things minimal: we persist a tiny dataset, run a parallel map
 that returns a nested DataModel, and display the result.
 """
 
-from typing import Optional
-
 from pydantic import Field
 
 import datachain as dc
@@ -17,12 +15,12 @@ import datachain as dc
 class Metric(dc.DataModel):
     """Represents a single computed metric with quality metadata."""
 
-    value: Optional[float] = Field(default=None, description="Computed metric value")
-    confidence: Optional[float] = Field(
+    value: float | None = Field(default=None, description="Computed metric value")
+    confidence: float | None = Field(
         default=None, description="Confidence / quality score"
     )
-    status: Optional[str] = Field(default=None, description="Processing status label")
-    metric_error: Optional[str] = Field(
+    status: str | None = Field(default=None, description="Processing status label")
+    metric_error: str | None = Field(
         default=None, description="Error message if metric computation failed"
     )
 

{datachain-0.34.6 → datachain-0.35.0}/pyproject.toml

@@ -11,14 +11,13 @@ license-files = ["LICENSE"]
 authors = [{name = "Dmitry Petrov", email = "support@dvc.org"}]
 classifiers = [
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
   "Development Status :: 2 - Pre-Alpha"
 ]
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dynamic = ["version"]
 dependencies = [
   "pyyaml",
@@ -314,10 +313,13 @@ max-complexity = 15
 
 [tool.ruff.lint.per-file-ignores]
 "examples/**" = ["INP001"]
+"src/datachain/lib/convert/python_to_sql.py" = ["UP035"]
+"src/datachain/lib/signal_schema.py" = ["UP035"]
 "!src/datachain/lib/dc.py" = ["D"]
 "tests/scripts/**" = ["INP001"]
 "tests/**" = ["DTZ"]
 "tests/examples/wds_data.py" = ["E501"]
+"tests/unit/lib/test_signal_schema.py" = ["UP006", "UP007", "UP035", "UP045"]
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"

{datachain-0.34.6 → datachain-0.35.0}/src/datachain/asyn.py

@@ -3,6 +3,7 @@ import threading
 from collections.abc import (
     AsyncIterable,
     Awaitable,
+    Callable,
     Coroutine,
     Generator,
     Iterable,
@@ -10,7 +11,7 @@ from collections.abc import (
 )
 from concurrent.futures import ThreadPoolExecutor, wait
 from heapq import heappop, heappush
-from typing import Any, Callable, Generic, Optional, TypeVar
+from typing import Any, Generic, TypeVar
 
 from fsspec.asyn import get_loop
 
@@ -49,7 +50,7 @@ class AsyncMapper(Generic[InputT, ResultT]):
         iterable: Iterable[InputT],
         *,
         workers: int = ASYNC_WORKERS,
-        loop: Optional[asyncio.AbstractEventLoop] = None,
+        loop: asyncio.AbstractEventLoop | None = None,
     ):
         self.func = func
         self.iterable = iterable
@@ -107,9 +108,7 @@ class AsyncMapper(Generic[InputT, ResultT]):
 
     async def init(self) -> None:
         self.work_queue = asyncio.Queue(2 * self.workers)
-        self.result_queue: asyncio.Queue[Optional[ResultT]] = asyncio.Queue(
-            self.workers
-        )
+        self.result_queue: asyncio.Queue[ResultT | None] = asyncio.Queue(self.workers)
 
     async def run(self) -> None:
         producer = self.start_task(self.produce())
@@ -149,10 +148,10 @@ class AsyncMapper(Generic[InputT, ResultT]):
             if exc:
                 raise exc
 
-    async def _pop_result(self) -> Optional[ResultT]:
+    async def _pop_result(self) -> ResultT | None:
         return await self.result_queue.get()
 
-    def next_result(self, timeout=None) -> Optional[ResultT]:
+    def next_result(self, timeout=None) -> ResultT | None:
         """
         Return the next available result.
 
@@ -212,17 +211,17 @@ class OrderedMapper(AsyncMapper[InputT, ResultT]):
         iterable: Iterable[InputT],
         *,
         workers: int = ASYNC_WORKERS,
-        loop: Optional[asyncio.AbstractEventLoop] = None,
+        loop: asyncio.AbstractEventLoop | None = None,
     ):
         super().__init__(func, iterable, workers=workers, loop=loop)
         self._waiters: dict[int, Any] = {}
-        self._getters: dict[int, asyncio.Future[Optional[ResultT]]] = {}
-        self.heap: list[tuple[int, Optional[ResultT]]] = []
+        self._getters: dict[int, asyncio.Future[ResultT | None]] = {}
+        self.heap: list[tuple[int, ResultT | None]] = []
         self._next_yield = 0
         self._items_seen = 0
         self._window = 2 * workers
 
-    def _push_result(self, i: int, result: Optional[ResultT]) -> None:
+    def _push_result(self, i: int, result: ResultT | None) -> None:
         if i in self._getters:
             future = self._getters.pop(i)
             future.set_result(result)
@@ -243,7 +242,7 @@ class OrderedMapper(AsyncMapper[InputT, ResultT]):
     async def init(self) -> None:
         self.work_queue = asyncio.Queue(2 * self.workers)
 
-    async def _pop_result(self) -> Optional[ResultT]:
+    async def _pop_result(self) -> ResultT | None:
         if self.heap and self.heap[0][0] == self._next_yield:
             _i, out = heappop(self.heap)
         else:

{datachain-0.34.6 → datachain-0.35.0}/src/datachain/cache.py

@@ -2,7 +2,7 @@ import os
 from collections.abc import Iterator
 from contextlib import contextmanager
 from tempfile import mkdtemp
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
 from dvc_data.hashfile.db.local import LocalHashFileDB
 from dvc_objects.fs.local import LocalFileSystem
@@ -22,14 +22,14 @@ def try_scandir(path):
         pass
 
 
-def get_temp_cache(tmp_dir: str, prefix: Optional[str] = None) -> "Cache":
+def get_temp_cache(tmp_dir: str, prefix: str | None = None) -> "Cache":
     cache_dir = mkdtemp(prefix=prefix, dir=tmp_dir)
     return Cache(cache_dir, tmp_dir=tmp_dir)
 
 
 @contextmanager
 def temporary_cache(
-    tmp_dir: str, prefix: Optional[str] = None, delete: bool = True
+    tmp_dir: str, prefix: str | None = None, delete: bool = True
 ) -> Iterator["Cache"]:
     cache = get_temp_cache(tmp_dir, prefix=prefix)
     try:
@@ -58,7 +58,7 @@ class Cache:  # noqa: PLW1641
     def tmp_dir(self):
         return self.odb.tmp_dir
 
-    def get_path(self, file: "File") -> Optional[str]:
+    def get_path(self, file: "File") -> str | None:
         if self.contains(file):
             return self.path_from_checksum(file.get_hash())
         return None
@@ -74,7 +74,7 @@ class Cache:  # noqa: PLW1641
         self.odb.delete(file.get_hash())
 
     async def download(
-        self, file: "File", client: "Client", callback: Optional[Callback] = None
+        self, file: "File", client: "Client", callback: Callback | None = None
     ) -> None:
         from dvc_objects.fs.utils import tmp_fname