datachain 0.25.2__py3-none-any.whl → 0.26.1__py3-none-any.whl

datachain/lib/file.py

@@ -43,7 +43,7 @@ logger = logging.getLogger("datachain")
 # how to create file path when exporting
 ExportPlacement = Literal["filename", "etag", "fullpath", "checksum"]
 
-FileType = Literal["binary", "text", "image", "video"]
+FileType = Literal["binary", "text", "image", "video", "audio"]
 EXPORT_FILES_MAX_THREADS = 5
 
 
@@ -312,6 +312,14 @@ class File(DataModel):
         file._set_stream(self._catalog, caching_enabled=self._caching_enabled)
         return file
 
+    def as_audio_file(self) -> "AudioFile":
+        """Convert the file to a `AudioFile` object."""
+        if isinstance(self, AudioFile):
+            return self
+        file = AudioFile(**self.model_dump())
+        file._set_stream(self._catalog, caching_enabled=self._caching_enabled)
+        return file
+
     @classmethod
     def upload(
         cls, data: bytes, path: str, catalog: Optional["Catalog"] = None
@@ -851,6 +859,157 @@ class VideoFile(File):
             start += duration
 
 
+class AudioFile(File):
+    """
+    A data model for handling audio files.
+
+    This model inherits from the `File` model and provides additional functionality
+    for reading audio files, extracting audio fragments, and splitting audio into
+    fragments.
+    """
+
+    def get_info(self) -> "Audio":
+        """
+        Retrieves metadata and information about the audio file. It does not
+        download the file if possible, only reads its header. It is thus might be
+        a good idea to disable caching and prefetching for UDF if you only need
+        audio metadata.
+
+        Returns:
+            Audio: A Model containing audio metadata such as duration,
+                   sample rate, channels, and codec details.
+        """
+        from .audio import audio_info
+
+        return audio_info(self)
+
+    def get_fragment(self, start: float, end: float) -> "AudioFragment":
+        """
+        Returns an audio fragment from the specified time range. It does not
+        download the file, neither it actually extracts the fragment. It returns
+        a Model representing the audio fragment, which can be used to read or save
+        it later.
+
+        Args:
+            start (float): The start time of the fragment in seconds.
+            end (float): The end time of the fragment in seconds.
+
+        Returns:
+            AudioFragment: A Model representing the audio fragment.
+        """
+        if start < 0 or end < 0 or start >= end:
+            raise ValueError(f"Invalid time range: ({start:.3f}, {end:.3f})")
+
+        return AudioFragment(audio=self, start=start, end=end)
+
+    def get_fragments(
+        self,
+        duration: float,
+        start: float = 0,
+        end: Optional[float] = None,
+    ) -> "Iterator[AudioFragment]":
+        """
+        Splits the audio into multiple fragments of a specified duration.
+
+        Args:
+            duration (float): The duration of each audio fragment in seconds.
+            start (float): The starting time in seconds (default: 0).
+            end (float, optional): The ending time in seconds. If None, the entire
+                                   remaining audio is processed (default: None).
+
+        Returns:
+            Iterator[AudioFragment]: An iterator yielding audio fragments.
+
+        Note:
+            If end is not specified, number of samples will be taken from the
+            audio file, this means audio file needs to be downloaded.
+        """
+        if duration <= 0:
+            raise ValueError("duration must be a positive float")
+        if start < 0:
+            raise ValueError("start must be a non-negative float")
+
+        if end is None:
+            end = self.get_info().duration
+
+        if end < 0:
+            raise ValueError("end must be a non-negative float")
+        if start >= end:
+            raise ValueError("start must be less than end")
+
+        while start < end:
+            yield self.get_fragment(start, min(start + duration, end))
+            start += duration
+
+
+class AudioFragment(DataModel):
+    """
+    A data model for representing an audio fragment.
+
+    This model represents a specific fragment within an audio file with defined
+    start and end times. It allows access to individual fragments and provides
+    functionality for reading and saving audio fragments as separate audio files.
+
+    Attributes:
+        audio (AudioFile): The audio file containing the audio fragment.
+        start (float): The starting time of the audio fragment in seconds.
+        end (float): The ending time of the audio fragment in seconds.
+    """
+
+    audio: AudioFile
+    start: float
+    end: float
+
+    def get_np(self) -> tuple["ndarray", int]:
+        """
+        Returns the audio fragment as a NumPy array with sample rate.
+
+        Returns:
+            tuple[ndarray, int]: A tuple containing the audio data as a NumPy array
+                               and the sample rate.
+        """
+        from .audio import audio_fragment_np
+
+        duration = self.end - self.start
+        return audio_fragment_np(self.audio, self.start, duration)
+
+    def read_bytes(self, format: str = "wav") -> bytes:
+        """
+        Returns the audio fragment as audio bytes.
+
+        Args:
+            format (str): The desired audio format (e.g., 'wav', 'mp3').
+                         Defaults to 'wav'.
+
+        Returns:
+            bytes: The encoded audio fragment as bytes.
+        """
+        from .audio import audio_fragment_bytes
+
+        duration = self.end - self.start
+        return audio_fragment_bytes(self.audio, self.start, duration, format)
+
+    def save(self, output: str, format: Optional[str] = None) -> "AudioFile":
+        """
+        Saves the audio fragment as a new audio file.
+
+        If `output` is a remote path, the audio file will be uploaded to remote storage.
+
+        Args:
+            output (str): The destination path, which can be a local file path
+                          or a remote URL.
+            format (str, optional): The output audio format (e.g., 'wav', 'mp3').
+                                    If None, the format is inferred from the
+                                    file extension.
+
+        Returns:
+            AudioFile: A Model representing the saved audio file.
+        """
+        from .audio import save_audio_fragment
+
+        return save_audio_fragment(self.audio, self.start, self.end, output, format)
+
+
 class VideoFrame(DataModel):
     """
     A data model for representing a video frame.
@@ -981,6 +1140,34 @@ class Video(DataModel):
     codec: str = Field(default="")
 
 
+class Audio(DataModel):
+    """
+    A data model representing metadata for an audio file.
+
+    Attributes:
+        sample_rate (int): The sample rate of the audio (samples per second).
+                          Defaults to -1 if unknown.
+        channels (int): The number of audio channels. Defaults to -1 if unknown.
+        duration (float): The total duration of the audio in seconds.
+                         Defaults to -1.0 if unknown.
+        samples (int): The total number of samples in the audio.
+                      Defaults to -1 if unknown.
+        format (str): The format of the audio file (e.g., 'wav', 'mp3').
+                     Defaults to an empty string.
+        codec (str): The codec used for encoding the audio. Defaults to an empty string.
+        bit_rate (int): The bit rate of the audio in bits per second.
+                       Defaults to -1 if unknown.
+    """
+
+    sample_rate: int = Field(default=-1)
+    channels: int = Field(default=-1)
+    duration: float = Field(default=-1.0)
+    samples: int = Field(default=-1)
+    format: str = Field(default="")
+    codec: str = Field(default="")
+    bit_rate: int = Field(default=-1)
+
+
 class ArrowRow(DataModel):
     """`DataModel` for reading row from Arrow-supported file."""
 
@@ -1018,5 +1205,7 @@ def get_file_type(type_: FileType = "binary") -> type[File]:
         file = ImageFile  # type: ignore[assignment]
     elif type_ == "video":
         file = VideoFile
+    elif type_ == "audio":
+        file = AudioFile
 
     return file

datachain/lib/model_store.py

@@ -81,3 +81,11 @@ class ModelStore:
         if val is None or not ModelStore.is_pydantic(val):
             return None
         return val
+
+    @staticmethod
+    def is_partial(parent_type) -> bool:
+        return (
+            parent_type
+            and ModelStore.is_pydantic(parent_type)
+            and "@" in ModelStore.get_name(parent_type)
+        )

datachain/lib/pytorch.py

@@ -125,7 +125,10 @@ class PytorchDataset(IterableDataset):
         ds = read_dataset(
             name=self.name, version=self.version, session=session
         ).settings(cache=self.cache, prefetch=self.prefetch)
-        ds = ds.remove_file_signals()
+
+        # remove file signals from dataset
+        schema = ds.signals_schema.clone_without_file_signals()
+        ds = ds.select(*schema.values.keys())
 
         if self.num_samples > 0:
             ds = ds.sample(self.num_samples)

datachain/lib/signal_schema.py

@@ -446,14 +446,14 @@ class SignalSchema:
                 res[db_name] = python_to_sql(type_)
         return res
 
-    def row_to_objs(self, row: Sequence[Any]) -> list[DataValue]:
+    def row_to_objs(self, row: Sequence[Any]) -> list[Any]:
         self._init_setup_values()
 
-        objs: list[DataValue] = []
+        objs: list[Any] = []
         pos = 0
         for name, fr_type in self.values.items():
-            if self.setup_values and (val := self.setup_values.get(name, None)):
-                objs.append(val)
+            if self.setup_values and name in self.setup_values:
+                objs.append(self.setup_values.get(name))
             elif (fr := ModelStore.to_pydantic(fr_type)) is not None:
                 j, pos = unflatten_to_json_pos(fr, row, pos)
                 objs.append(fr(**j))
@@ -589,6 +589,9 @@ class SignalSchema:
         ]
 
         if name:
+            if "." in name:
+                name = name.replace(".", "__")
+
             signals = [
                 s
                 for s in signals
@@ -607,24 +610,38 @@ class SignalSchema:
         return SignalSchema(schema)
 
     def _find_in_tree(self, path: list[str]) -> DataType:
+        if val := self.tree.get(".".join(path)):
+            # If the path is a single string, we can directly access it
+            # without traversing the tree.
+            return val[0]
+
         curr_tree = self.tree
         curr_type = None
         i = 0
         while curr_tree is not None and i < len(path):
             if val := curr_tree.get(path[i]):
                 curr_type, curr_tree = val
-            elif i == 0 and len(path) > 1 and (val := curr_tree.get(".".join(path))):
-                curr_type, curr_tree = val
-                break
             else:
                 curr_type = None
+                break
             i += 1
 
-        if curr_type is None:
+        if curr_type is None or i < len(path):
+            # If we reached the end of the path and didn't find a type,
+            # or if we didn't traverse the entire path, raise an error.
             raise SignalResolvingError(path, "is not found")
 
         return curr_type
 
+    def group_by(
+        self, partition_by: Sequence[str], new_column: Sequence[Column]
+    ) -> "SignalSchema":
+        orig_schema = SignalSchema(copy.deepcopy(self.values))
+        schema = orig_schema.to_partial(*partition_by)
+
+        vals = {c.name: sql_to_python(c) for c in new_column}
+        return SignalSchema(schema.values | vals)
+
     def select_except_signals(self, *args: str) -> "SignalSchema":
         def has_signal(signal: str):
             signal = signal.replace(".", DEFAULT_DELIMITER)
@@ -888,7 +905,7 @@ class SignalSchema:
 
         return res
 
-    def to_partial(self, *columns: str) -> "SignalSchema":
+    def to_partial(self, *columns: str) -> "SignalSchema":  # noqa: C901
         """
         Convert the schema to a partial schema with only the specified columns.
 
@@ -931,9 +948,15 @@ class SignalSchema:
         partial_versions: dict[str, int] = {}
 
         def _type_name_to_partial(signal_name: str, type_name: str) -> str:
-            if "@" not in type_name:
+            # Check if we need to create a partial for this type
+            # Only create partials for custom types that are in the custom_types dict
+            if type_name not in custom_types:
                 return type_name
-            model_name, _ = ModelStore.parse_name_version(type_name)
+
+            if "@" in type_name:
+                model_name, _ = ModelStore.parse_name_version(type_name)
+            else:
+                model_name = type_name
 
             if signal_name not in signal_partials:
                 partial_versions.setdefault(model_name, 0)
@@ -957,6 +980,14 @@ class SignalSchema:
                     parent_type_partial = _type_name_to_partial(signal, parent_type)
 
                     schema[signal] = parent_type_partial
+
+                    # If this is a complex signal without field specifier (just "file")
+                    # and it's a custom type, include the entire complex signal
+                    if len(column_parts) == 1 and parent_type in custom_types:
+                        # Include the entire complex signal - no need to create partial
+                        schema[signal] = parent_type
+                        continue
+
                     continue
 
                 if parent_type not in custom_types:
@@ -971,6 +1002,20 @@ class SignalSchema:
                         f"Field {signal} not found in custom type {parent_type}"
                     )
 
+                # Check if this is the last part and if the column type is a complex
+                is_last_part = i == len(column_parts) - 1
+                is_complex_signal = signal_type in custom_types
+
+                if is_last_part and is_complex_signal:
+                    schema[column] = signal_type
+                    # Also need to remove the partial schema entry we created for the
+                    # parent since we're promoting the nested complex column to root
+                    parent_signal = column_parts[0]
+                    schema.pop(parent_signal, None)
+                    # Don't create partial types for this case
+                    break
+
+                # Create partial type for this field
                 partial_type = _type_name_to_partial(
                     ".".join(column_parts[: i + 1]),
                     signal_type,

datachain/lib/udf.py

@@ -13,8 +13,7 @@ from datachain.asyn import AsyncMapper
 from datachain.cache import temporary_cache
 from datachain.dataset import RowDict
 from datachain.lib.convert.flatten import flatten
-from datachain.lib.data_model import DataValue
-from datachain.lib.file import File
+from datachain.lib.file import DataModel, File
 from datachain.lib.utils import AbstractUDF, DataChainError, DataChainParamsError
 from datachain.query.batch import (
     Batch,
@@ -266,15 +265,28 @@ class UDFBase(AbstractUDF):
 
     def _parse_row(
         self, row_dict: RowDict, catalog: "Catalog", cache: bool, download_cb: Callback
-    ) -> list[DataValue]:
+    ) -> list[Any]:
         assert self.params
         row = [row_dict[p] for p in self.params.to_udf_spec()]
         obj_row = self.params.row_to_objs(row)
         for obj in obj_row:
-            if isinstance(obj, File):
-                obj._set_stream(catalog, caching_enabled=cache, download_cb=download_cb)
+            self._set_stream_recursive(obj, catalog, cache, download_cb)
         return obj_row
 
+    def _set_stream_recursive(
+        self, obj: Any, catalog: "Catalog", cache: bool, download_cb: Callback
+    ) -> None:
+        """Recursively set the catalog stream on all File objects within an object."""
+        if isinstance(obj, File):
+            obj._set_stream(catalog, caching_enabled=cache, download_cb=download_cb)
+
+        # Check all fields for nested File objects, but only for DataModel objects
+        if isinstance(obj, DataModel):
+            for field_name in obj.model_fields:
+                field_value = getattr(obj, field_name, None)
+                if isinstance(field_value, DataModel):
+                    self._set_stream_recursive(field_value, catalog, cache, download_cb)
+
     def _prepare_row(self, row, udf_fields, catalog, cache, download_cb):
         row_dict = RowDict(zip(udf_fields, row))
         return self._parse_row(row_dict, catalog, cache, download_cb)

datachain/query/dataset.py

@@ -559,7 +559,13 @@ class UDFStep(Step, ABC):
         """
         Create temporary table with group by partitions.
         """
+        # Check if partition_by is set, we need it to create partitions.
         assert self.partition_by is not None
+        # Check if sys__id is in the query, we need it to be able to join
+        # the partition table with the udf table later.
+        assert any(c.name == "sys__id" for c in query.selected_columns), (
+            "Query must have sys__id column to use partitioning."
+        )
 
         if isinstance(self.partition_by, (list, tuple, GeneratorType)):
             list_partition_by = list(self.partition_by)
@@ -606,6 +612,22 @@ class UDFStep(Step, ABC):
 
         # Apply partitioning if needed.
         if self.partition_by is not None:
+            if not any(c.name == "sys__id" for c in query.selected_columns):
+                # If sys__id is not in the query, we need to create a temp table
+                # to hold the query results, so we can join it with the
+                # partition table later.
+                columns = [
+                    c if isinstance(c, Column) else Column(c.name, c.type)
+                    for c in query.subquery().columns
+                ]
+                temp_table = self.catalog.warehouse.create_dataset_rows_table(
+                    self.catalog.warehouse.temp_table_name(),
+                    columns=columns,
+                )
+                temp_tables.append(temp_table.name)
+                self.catalog.warehouse.copy_table(temp_table, query)
+                _query = query = temp_table.select()
+
             partition_tbl = self.create_partitions_table(query)
             temp_tables.append(partition_tbl.name)
             query = query.outerjoin(
@@ -1031,16 +1053,22 @@ class SQLGroupBy(SQLClause):
             c.get_column() if isinstance(c, Function) else c for c in self.group_by
         ]
 
-        cols = [
-            c.get_column()
-            if isinstance(c, Function)
-            else subquery.c[str(c)]
-            if isinstance(c, (str, C))
-            else c
-            for c in (*group_by, *self.cols)
-        ]
+        cols_dict: dict[str, Any] = {}
+        for c in (*group_by, *self.cols):
+            if isinstance(c, Function):
+                key = c.name
+                value = c.get_column()
+            elif isinstance(c, (str, C)):
+                key = str(c)
+                value = subquery.c[str(c)]
+            else:
+                key = c.name
+                value = c  # type: ignore[assignment]
+            cols_dict[key] = value
+
+        unique_cols = cols_dict.values()
 
-        return sqlalchemy.select(*cols).select_from(subquery).group_by(*group_by)
+        return sqlalchemy.select(*unique_cols).select_from(subquery).group_by(*group_by)
 
 
 def _validate_columns(

{datachain-0.25.2.dist-info → datachain-0.26.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.25.2
+Version: 0.26.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -63,6 +63,9 @@ Provides-Extra: torch
 Requires-Dist: torch>=2.1.0; extra == "torch"
 Requires-Dist: torchvision; extra == "torch"
 Requires-Dist: transformers>=4.36.0; extra == "torch"
+Provides-Extra: audio
+Requires-Dist: torchaudio; extra == "audio"
+Requires-Dist: soundfile; extra == "audio"
 Provides-Extra: remote
 Requires-Dist: lz4; extra == "remote"
 Requires-Dist: requests>=2.22.0; extra == "remote"
@@ -78,7 +81,7 @@ Requires-Dist: ffmpeg-python; extra == "video"
 Requires-Dist: imageio[ffmpeg,pyav]>=2.37.0; extra == "video"
 Requires-Dist: opencv-python; extra == "video"
 Provides-Extra: tests
-Requires-Dist: datachain[hf,remote,torch,vector,video]; extra == "tests"
+Requires-Dist: datachain[audio,hf,remote,torch,vector,video]; extra == "tests"
 Requires-Dist: pytest<9,>=8; extra == "tests"
 Requires-Dist: pytest-sugar>=0.9.6; extra == "tests"
 Requires-Dist: pytest-cov>=4.1.0; extra == "tests"
@@ -108,6 +111,7 @@ Requires-Dist: accelerate; extra == "examples"
 Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
 Requires-Dist: ultralytics; extra == "examples"
 Requires-Dist: open_clip_torch; extra == "examples"
+Requires-Dist: openai; extra == "examples"
 Dynamic: license-file
 
 ================

{datachain-0.25.2.dist-info → datachain-0.26.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=ofXacfzLKYzTqU1oyHz5xZi1L4skQCoJdUMC4YARenk,1616
+datachain/__init__.py,sha256=2TZ8ptSB9BtnYF31mDEhWG9N16EQ5pf9vNqQaFr2txs,1712
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
 datachain/cache.py,sha256=ESVRaCJXEThMIfGEFVHx6wJPOZA7FYk9V6WxjyuqUBY,3626
@@ -23,7 +23,7 @@ datachain/utils.py,sha256=DNqOi-Ydb7InyWvD9m7_yailxz6-YGpZzh00biQaHNo,15305
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
 datachain/catalog/catalog.py,sha256=QTWCXy75iWo-0MCXyfV_WbsKeZ1fpLpvL8d60rxn1ws,65528
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
-datachain/catalog/loader.py,sha256=UXjYD6BNRoupPvkiz3-b04jepXhtLHCA4gzKFnXxOtQ,5987
+datachain/catalog/loader.py,sha256=B2cps5coFE4MBttM-j8cs7JgNVPjnHKF4Gx1s2fJrxw,6119
 datachain/cli/__init__.py,sha256=WvBqnwjG8Wp9xGCn-4eqfoZ3n7Sj1HJemCi4MayJh_c,8221
 datachain/cli/utils.py,sha256=wrLnAh7Wx8O_ojZE8AE4Lxn5WoxHbOj7as8NWlLAA74,3036
 datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQaRlIhI,493
@@ -58,11 +58,11 @@ datachain/diff/__init__.py,sha256=-OFZzgOplqO84iWgGY7kfe60NXaWR9JRIh9T-uJboAM,96
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/fs/reference.py,sha256=A8McpXF0CqbXPqanXuvpKu50YLB3a2ZXA3YAPxtBXSM,914
 datachain/fs/utils.py,sha256=s-FkTOCGBk-b6TT3toQH51s9608pofoFjUSTc1yy7oE,825
-datachain/func/__init__.py,sha256=CjNLHfJkepdXdRZ6HjJBjNSIjOeFMuMkwPDaPUrM75g,1270
+datachain/func/__init__.py,sha256=9K2MEC1NclY_zWuqevfEUOcrSE26cXDVnGqhNTj4lF8,1288
 datachain/func/aggregate.py,sha256=fmVEKf3MUR29dEgllGdtl6nG7Lwz-SiyA5X1EyRRNUk,12456
 datachain/func/array.py,sha256=fz5NUIPkp_KZ7tadCqJQSSJwWMYXEfYn60QkG2epC3k,13627
 datachain/func/base.py,sha256=wA0sBQAVyN9LPxoo7Ox83peS0zUVnyuKxukwAcjGLfY,534
-datachain/func/conditional.py,sha256=bzIZRSpVpe-lrHoWPTCA7bzZ-AHtR44BVM82hqD1pY0,9188
+datachain/func/conditional.py,sha256=9YYurD_PBMyf5rR9dj2gLv-Lo7UhYfHW6EtrUErVpz8,10165
 datachain/func/func.py,sha256=fpslnn4edr0dH3mD8BSTndRFJiiVZvbJoBJV6HkHMqw,17400
 datachain/func/numeric.py,sha256=J6FgzuIAcS6B02Cm1qPnJdB6ut21jyBDVXSBrkZNZaQ,6978
 datachain/func/path.py,sha256=9Jas35QhEtRai4l54hMqVvuJsqxHvOx88oo4vym1H_I,4077
@@ -71,24 +71,25 @@ datachain/func/string.py,sha256=X9u4ip97U63RCaKRhMddoze7HgPiY3LbPRn9G06UWWo,7311
 datachain/func/window.py,sha256=ImyRpc1QI8QUSPO7KdD60e_DPVo7Ja0G5kcm6BlyMcw,1584
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/arrow.py,sha256=hdEQ8I1JgNmEAaXTaqaU1qvZDi5dgtes1IC69ycthz8,10753
+datachain/lib/audio.py,sha256=J7XJ14ItPF9y6pN-tmMV9In9X9rgwlBwzyzdGOUkPGk,4376
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=ZwBXELtqROEdLL4DmxTipnwUZmhQvMz_UVDzyf7nQ9Y,2899
 datachain/lib/dataset_info.py,sha256=7w-DoKOyIVoOtWGCgciMLcP5CiAWJB3rVI-vUDF80k0,3311
-datachain/lib/file.py,sha256=gTzJXaGIyFOrw_B4yiOEs7U23n4oAQuWDI2v9KWwp2o,33889
+datachain/lib/file.py,sha256=tHBBacsh1580UPFC6fAINBNwNiyymNgzj89rpsz1LKc,40817
 datachain/lib/hf.py,sha256=_dCoGTv7n5cBgxhCDfZI-t3hnMCXGHd6sEsxRThcizE,5754
 datachain/lib/image.py,sha256=erWvZW5M3emnbl6_fGAOPyKm-1EKbt3vOdWPfe3Oo7U,3265
 datachain/lib/listing.py,sha256=U-2stsTEwEsq4Y80dqGfktGzkmB5-ZntnL1_rzXlH0k,7089
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=zdyg6XLk3QIsSk3I7s0Ez5kaCJSlE3uq7JiGxf7UwtU,6348
-datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
+datachain/lib/model_store.py,sha256=dkL2rcT5ag-kbgkhQPL_byEs-TCYr29qvdltroL5NxM,2734
 datachain/lib/namespaces.py,sha256=it52UbbwB8dzhesO2pMs_nThXiPQ1Ph9sD9I3GQkg5s,2099
 datachain/lib/projects.py,sha256=8lN0qV8czX1LGtWURCUvRlSJk-RpO9w9Rra_pOZus6g,2595
-datachain/lib/pytorch.py,sha256=oBBd6cxYrcwaFz7IQajKqhGqDdNnwUZWs0wJPRizrjk,7712
+datachain/lib/pytorch.py,sha256=S-st2SAczYut13KMf6eSqP_OQ8otWI5TRmzhK5fN3k0,7828
 datachain/lib/settings.py,sha256=9wi0FoHxRxNiyn99pR28IYsMkoo47jQxeXuObQr2Ar0,2929
-datachain/lib/signal_schema.py,sha256=dVEqqrQQ_BS3yzU_49-Gari7IjVyMl1UT8h1WIsZabs,36489
+datachain/lib/signal_schema.py,sha256=tOWcWEG0ZwiU0qxywEYs3qkTexQQHmzg28wZ1CJGyEI,38552
 datachain/lib/tar.py,sha256=MLcVjzIgBqRuJacCNpZ6kwSZNq1i2tLyROc8PVprHsA,999
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=3uITkhO8IZnX49aePheObzd5ORYi2DIDYZVMQlBAJ-s,16687
+datachain/lib/udf.py,sha256=nkcB3HNtSteUspwsGmOKyy3mH2F-Sfo6iW64-Ep47-I,17299
 datachain/lib/udf_signature.py,sha256=Yz20iJ-WF1pijT3hvcDIKFzgWV9gFxZM73KZRx3NbPk,7560
 datachain/lib/utils.py,sha256=rG2y7NwTqZOuomZZRmrA-Q-ANM_j1cToQYqDJoOeGyU,1480
 datachain/lib/video.py,sha256=u6fLJWj5G6QqsVkpfHnKGklBNpG3BRRg6v3izngnNcU,6767
@@ -97,13 +98,13 @@ datachain/lib/webdataset_laion.py,sha256=xvT6m_r5y0KbOx14BUe7UC5mOgrktJq53Mh-H0E
 datachain/lib/convert/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/convert/flatten.py,sha256=IZFiUYbgXSxXhPSG5Cqf5IjnJ4ZDZKXMr4o_yCR1NY4,1505
 datachain/lib/convert/python_to_sql.py,sha256=wg-O5FRKX3x3Wh8ZL1b9ntMlgf1zRO4djMP3t8CHJLo,3188
-datachain/lib/convert/sql_to_python.py,sha256=XXCBYDQFUXJIBNWkjEP944cnCfJ8GF2Tji0DLF3A_zQ,315
+datachain/lib/convert/sql_to_python.py,sha256=Gxc4FylWC_Pvvuawuc2MKZIiuAWI7wje8pyeN1MxRrU,670
 datachain/lib/convert/unflatten.py,sha256=ysMkstwJzPMWUlnxn-Z-tXJR3wmhjHeSN_P-sDcLS6s,2010
 datachain/lib/convert/values_to_tuples.py,sha256=j5yZMrVUH6W7b-7yUvdCTGI7JCUAYUOzHUGPoyZXAB0,4360
 datachain/lib/dc/__init__.py,sha256=TFci5HTvYGjBesNUxDAnXaX36PnzPEUSn5a6JxB9o0U,872
 datachain/lib/dc/csv.py,sha256=q6a9BpapGwP6nwy6c5cklxQumep2fUp9l2LAjtTJr6s,4411
 datachain/lib/dc/database.py,sha256=g5M6NjYR1T0vKte-abV-3Ejnm-HqxTIMir5cRi_SziE,6051
-datachain/lib/dc/datachain.py,sha256=_FJnpgNN_b2xz39MsgeS0NTto0hzpcFPbJlaUBLcqTs,87094
+datachain/lib/dc/datachain.py,sha256=ap54lcuj71tvp0zX1jiFFiEWvA5UPeyYJRJkd2APmlI,92897
 datachain/lib/dc/datasets.py,sha256=P6CIJizD2IYFwOQG5D3VbQRjDmUiRH0ysdtb551Xdm8,15098
 datachain/lib/dc/hf.py,sha256=PJl2wiLjdRsMz0SYbLT-6H8b-D5i2WjeH7li8HHOk_0,2145
 datachain/lib/dc/json.py,sha256=dNijfJ-H92vU3soyR7X1IiDrWhm6yZIGG3bSnZkPdAE,2733
@@ -125,7 +126,7 @@ datachain/model/ultralytics/pose.py,sha256=pBlmt63Qe68FKmexHimUGlNbNOoOlMHXG4fzX
 datachain/model/ultralytics/segment.py,sha256=63bDCj43E6iZ0hFI5J6uQfksdCmjEp6sEm1XzVaE8pw,2986
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=-goxLpE0EUvaDHu66rstj53UnfHpYfBUGux8GSpJ93k,4306
-datachain/query/dataset.py,sha256=t9EWZkJGPRPcBvKOsFO7ZiaTeUXc8YuTZydRbcv83_E,61350
+datachain/query/dataset.py,sha256=cYNrg1QyrZpO-oup3mqmSYHUvgEYBKe8RgkVbyQa6p0,62777
 datachain/query/dispatch.py,sha256=A0nPxn6mEN5d9dDo6S8m16Ji_9IvJLXrgF2kqXdi4fs,15546
 datachain/query/metrics.py,sha256=DOK5HdNVaRugYPjl8qnBONvTkwjMloLqAr7Mi3TjCO0,858
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -157,9 +158,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.25.2.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.25.2.dist-info/METADATA,sha256=aA1Ee1umcPyEXMzrdlhNexDW1rq2zRo2IJHAKyOJwN4,13385
-datachain-0.25.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.25.2.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.25.2.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.25.2.dist-info/RECORD,,
+datachain-0.26.1.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.26.1.dist-info/METADATA,sha256=C0Pb9d9IcJ6oOPXihcyEhTc_Rf7Fe4pP_anKhC3JfeU,13543
+datachain-0.26.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.26.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.26.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.26.1.dist-info/RECORD,,