datachain 0.3.19__tar.gz → 0.4.0__tar.gz

{datachain-0.3.19 → datachain-0.4.0}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.5'
+    rev: 'v0.6.7'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.3.19/src/datachain.egg-info → datachain-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.19
+Version: 0.4.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.3.19 → datachain-0.4.0}/mkdocs.yml

@@ -15,6 +15,7 @@ validation:
 
 theme:
   name: material
+  custom_dir: overrides
   logo: assets/datachain-white.svg
   favicon: assets/datachain.svg
   icon:
@@ -71,6 +72,7 @@ nav:
       - references/udf.md
       - references/torch.md
       - references/sql.md
+  - DataChain Website: https://datachain.ai" target="_blank"
 
 markdown_extensions:
   - abbr

datachain-0.4.0/overrides/main.html

@@ -0,0 +1,12 @@
+{% extends "base.html" %}
+
+{% block scripts %}
+
+{{ super() }}
+
+<script type="text/javascript">
+  !function () { var e, t, n; e = "14ffd92a6cbf5f2", t = function () { Reo.init({ clientID: "14ffd92a6cbf5f2" }) }, (n = document.createElement("script")).src = "https://static.reo.dev/" + e + "/reo.js", n.async = !0, n.onload = t, document.head.appendChild(n) }();
+</script>
+
+
+{% endblock %}

{datachain-0.3.19 → datachain-0.4.0}/src/datachain/catalog/catalog.py

@@ -79,6 +79,7 @@ if TYPE_CHECKING:
     )
     from datachain.dataset import DatasetVersion
     from datachain.job import Job
+    from datachain.lib.file import File
 
 logger = logging.getLogger("datachain")
 
@@ -978,7 +979,6 @@ class Catalog:
         script_output="",
         create_rows_table=True,
         job_id: Optional[str] = None,
-        is_job_result: bool = False,
     ) -> DatasetRecord:
         """
         Creates dataset version if it doesn't exist.
@@ -1000,7 +1000,6 @@ class Catalog:
             script_output=script_output,
             schema=schema,
             job_id=job_id,
-            is_job_result=is_job_result,
             ignore_if_exists=True,
         )
 
@@ -1210,7 +1209,6 @@ class Catalog:
             size=dataset_version.size,
             preview=dataset_version.preview,
             job_id=dataset_version.job_id,
-            is_job_result=dataset_version.is_job_result,
         )
         # to avoid re-creating rows table, we are just renaming it for a new version
         # of target dataset
@@ -1399,65 +1397,34 @@ class Catalog:
         dataset = self.get_dataset(name)
         return self.update_dataset(dataset, **update_data)
 
-    def get_file_signals(
-        self, dataset_name: str, dataset_version: int, row: RowDict
-    ) -> Optional[RowDict]:
+    def get_file_from_row(
+        self, dataset_name: str, dataset_version: int, row: RowDict, signal_name: str
+    ) -> "File":
         """
-        Function that returns file signals from dataset row.
-        Note that signal names are without prefix, so if there was 'laion__file__source'
-        in original row, result will have just 'source'
-        Example output:
-            {
-                "source": "s3://ldb-public",
-                "path": "animals/dogs/dog.jpg",
-                ...
-            }
+        Function that returns specific file signal from dataset row by name.
         """
         from datachain.lib.file import File
         from datachain.lib.signal_schema import DEFAULT_DELIMITER, SignalSchema
 
         version = self.get_dataset(dataset_name).get_version(dataset_version)
-
-        file_signals_values = RowDict()
-
         schema = SignalSchema.deserialize(version.feature_schema)
-        for file_signals in schema.get_signals(File):
-            prefix = file_signals.replace(".", DEFAULT_DELIMITER) + DEFAULT_DELIMITER
-            file_signals_values[file_signals] = {
-                c_name.removeprefix(prefix): c_value
-                for c_name, c_value in row.items()
-                if c_name.startswith(prefix)
-                and DEFAULT_DELIMITER not in c_name.removeprefix(prefix)
-            }
 
-        if not file_signals_values:
-            return None
-
-        # there can be multiple file signals in a schema, but taking the first
-        # one for now. In future we might add ability to choose from which one
-        # to open object
-        return next(iter(file_signals_values.values()))
-
-    def open_object(
-        self,
-        dataset_name: str,
-        dataset_version: int,
-        row: RowDict,
-        use_cache: bool = True,
-        **config: Any,
-    ):
-        from datachain.lib.file import File
+        if signal_name not in schema.get_signals(File):
+            raise RuntimeError(
+                f"File signal with path {signal_name} not found in ",
+                f"dataset {dataset_name}@v{dataset_version} signals schema",
+            )
 
-        file_signals = self.get_file_signals(dataset_name, dataset_version, row)
-        if not file_signals:
-            raise RuntimeError("Cannot open object without file signals")
+        prefix = signal_name.replace(".", DEFAULT_DELIMITER) + DEFAULT_DELIMITER
+        file_signals = {
+            c_name.removeprefix(prefix): c_value
+            for c_name, c_value in row.items()
+            if c_name.startswith(prefix)
+            and DEFAULT_DELIMITER not in c_name.removeprefix(prefix)
+            and c_name.removeprefix(prefix) in File.model_fields
+        }
 
-        config = config or self.client_config
-        client = self.get_client(file_signals["source"], **config)
-        return client.open_object(
-            File._from_row(file_signals),
-            use_cache=use_cache,
-        )
+        return File(**file_signals)
 
     def ls(
         self,

{datachain-0.3.19 → datachain-0.4.0}/src/datachain/data_storage/metastore.py

@@ -243,7 +243,6 @@ class AbstractMetastore(ABC, Serializable):
         size: Optional[int] = None,
         preview: Optional[list[dict]] = None,
         job_id: Optional[str] = None,
-        is_job_result: bool = False,
     ) -> DatasetRecord:
         """Creates new dataset version."""
 
@@ -497,7 +496,6 @@ class AbstractDBMetastore(AbstractMetastore):
             Column("query_script", Text, nullable=False, default=""),
             Column("schema", JSON, nullable=True),
             Column("job_id", Text, nullable=True),
-            Column("is_job_result", Boolean, nullable=False, default=False),
             UniqueConstraint("dataset_id", "version"),
         ]
 
@@ -1009,7 +1007,6 @@ class AbstractDBMetastore(AbstractMetastore):
         size: Optional[int] = None,
         preview: Optional[list[dict]] = None,
         job_id: Optional[str] = None,
-        is_job_result: bool = False,
         conn=None,
     ) -> DatasetRecord:
         """Creates new dataset version."""
@@ -1035,7 +1032,6 @@ class AbstractDBMetastore(AbstractMetastore):
             size=size,
             preview=json.dumps(preview or []),
             job_id=job_id or os.getenv("DATACHAIN_JOB_ID"),
-            is_job_result=is_job_result,
         )
         if ignore_if_exists and hasattr(query, "on_conflict_do_nothing"):
             # SQLite and PostgreSQL both support 'on_conflict_do_nothing',

{datachain-0.3.19 → datachain-0.4.0}/src/datachain/dataset.py

@@ -179,7 +179,6 @@ class DatasetVersion:
     sources: str = ""
     query_script: str = ""
     job_id: Optional[str] = None
-    is_job_result: bool = False
 
     @classmethod
     def parse(  # noqa: PLR0913
@@ -201,7 +200,6 @@ class DatasetVersion:
         sources: str = "",
         query_script: str = "",
         job_id: Optional[str] = None,
-        is_job_result: bool = False,
     ):
         return cls(
             id,
@@ -221,7 +219,6 @@ class DatasetVersion:
             sources,
             query_script,
             job_id,
-            is_job_result,
         )
 
     def __eq__(self, other):
@@ -327,7 +324,6 @@ class DatasetRecord:
         version_query_script: Optional[str],
         version_schema: str,
         version_job_id: Optional[str] = None,
-        version_is_job_result: bool = False,
     ) -> "DatasetRecord":
         labels_lst: list[str] = json.loads(labels) if labels else []
         schema_dct: dict[str, Any] = json.loads(schema) if schema else {}
@@ -353,7 +349,6 @@ class DatasetRecord:
             version_sources,  # type: ignore[arg-type]
             version_query_script,  # type: ignore[arg-type]
             version_job_id,
-            version_is_job_result,
         )
 
         return cls(

{datachain-0.3.19 → datachain-0.4.0/src/datachain.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.19
+Version: 0.4.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.3.19 → datachain-0.4.0}/src/datachain.egg-info/SOURCES.txt

@@ -48,6 +48,7 @@ examples/multimodal/hf_pipeline.py
 examples/multimodal/openai_image_desc_lib.py
 examples/multimodal/wds.py
 examples/multimodal/wds_filtered.py
+overrides/main.html
 src/datachain/__init__.py
 src/datachain/__main__.py
 src/datachain/asyn.py

{datachain-0.3.19 → datachain-0.4.0}/tests/func/test_catalog.py

@@ -847,7 +847,7 @@ def test_garbage_collect(cloud_test_catalog, from_cli, capsys):
     assert catalog.get_temp_table_names() == []
 
 
-def test_get_file_signals(cloud_test_catalog, dogs_dataset):
+def test_get_file_from_row(cloud_test_catalog, dogs_dataset):
     catalog = cloud_test_catalog.catalog
     catalog.metastore.update_dataset_version(
         dogs_dataset,
@@ -863,18 +863,22 @@ def test_get_file_signals(cloud_test_catalog, dogs_dataset):
         "name": "Jon",
         "age": 25,
         "f1__source": "s3://first_bucket",
-        "f1__name": "image1.jpg",
+        "f1__path": "image1.jpg",
         "f2__source": "s3://second_bucket",
-        "f2__name": "image2.jpg",
+        "f2__path": "image2.jpg",
     }
 
-    assert catalog.get_file_signals(dogs_dataset.name, 1, row) == {
-        "source": "s3://first_bucket",
-        "name": "image1.jpg",
-    }
+    assert catalog.get_file_from_row(dogs_dataset.name, 1, row, "f1") == File(
+        source="s3://first_bucket",
+        path="image1.jpg",
+    )
+    assert catalog.get_file_from_row(dogs_dataset.name, 1, row, "f2") == File(
+        source="s3://second_bucket",
+        path="image2.jpg",
+    )
 
 
-def test_get_file_signals_with_custom_types(cloud_test_catalog, dogs_dataset):
+def test_get_file_from_row_with_custom_types(cloud_test_catalog, dogs_dataset):
     catalog = cloud_test_catalog.catalog
     catalog.metastore.update_dataset_version(
         dogs_dataset,
@@ -885,7 +889,7 @@ def test_get_file_signals_with_custom_types(cloud_test_catalog, dogs_dataset):
             "f1": "File@v1",
             "f2": "File@v1",
             "_custom_types": {
-                "File@v1": {"source": "str", "name": "str"},
+                "File@v1": {"source": "str", "path": "str"},
             },
         },
     )
@@ -893,36 +897,18 @@ def test_get_file_signals_with_custom_types(cloud_test_catalog, dogs_dataset):
         "name": "Jon",
         "age": 25,
         "f1__source": "s3://first_bucket",
-        "f1__name": "image1.jpg",
+        "f1__path": "image1.jpg",
         "f2__source": "s3://second_bucket",
-        "f2__name": "image2.jpg",
-    }
-
-    assert catalog.get_file_signals(dogs_dataset.name, 1, row) == {
-        "source": "s3://first_bucket",
-        "name": "image1.jpg",
+        "f2__path": "image2.jpg",
     }
 
-
-def test_get_file_signals_no_signals(cloud_test_catalog, dogs_dataset):
-    catalog = cloud_test_catalog.catalog
-    catalog.metastore.update_dataset_version(
-        dogs_dataset,
-        1,
-        feature_schema={
-            "name": "str",
-            "age": "str",
-        },
+    assert catalog.get_file_from_row(dogs_dataset.name, 1, row, "f1") == File(
+        source="s3://first_bucket",
+        path="image1.jpg",
     )
-    row = {
-        "name": "Jon",
-        "age": 25,
-    }
-
-    assert catalog.get_file_signals(dogs_dataset.name, 1, row) is None
 
 
-def test_open_object_no_file_signals(cloud_test_catalog, dogs_dataset):
+def test_get_file_from_row_no_signals(cloud_test_catalog, dogs_dataset):
     catalog = cloud_test_catalog.catalog
     catalog.metastore.update_dataset_version(
         dogs_dataset,
@@ -938,4 +924,4 @@ def test_open_object_no_file_signals(cloud_test_catalog, dogs_dataset):
     }
 
     with pytest.raises(RuntimeError):
-        assert catalog.open_object(dogs_dataset.name, 1, row)
+        assert catalog.get_file_from_row(dogs_dataset.name, 1, row, "missing")

{datachain-0.3.19 → datachain-0.4.0}/tests/unit/test_query.py

@@ -39,7 +39,7 @@ def test_args(catalog, mock_popen):
     mock_popen.assert_called_once_with(["mypython", "-c", "pass"], env=expected_env)
 
 
-def test_capture_output(mocker, catalog, mock_popen):
+def test_capture_output(catalog, mock_popen):
     mock_popen.stdout = io.BytesIO(b"Hello, World!\rLorem Ipsum\nDolor Sit Amet\nconse")
     lines = []