datachain 0.26.3__py3-none-any.whl → 0.27.0__py3-none-any.whl

datachain/cli/parser/job.py

@@ -17,7 +17,12 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
     )
 
     studio_run_help = "Run a job in Studio"
-    studio_run_description = "Run a job in Studio."
+    studio_run_description = "Run a job in Studio. \n"
+    studio_run_description += (
+        "When using --start-time or --cron,"
+        " the job is scheduled to run but won't start immediately"
+        " (can be seen in the Tasks tab in UI)"
+    )
 
     studio_run_parser = jobs_subparser.add_parser(
         "run",
@@ -96,6 +101,14 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
         help="Priority for the job in range 0-5. "
         "Lower value is higher priority (default: 5)",
     )
+    studio_run_parser.add_argument(
+        "--start-time",
+        action="store",
+        help="Time to schedule a task in YYYY-MM-DDTHH:mm format or natural language.",
+    )
+    studio_run_parser.add_argument(
+        "--cron", action="store", help="Cron expression for the cron task."
+    )
 
     studio_ls_help = "List jobs in Studio"
     studio_ls_description = "List jobs in Studio."

datachain/lib/arrow.py

@@ -245,7 +245,7 @@ def arrow_type_mapper(col_type: pa.DataType, column: str = "") -> type:  # noqa:
             if field.nullable and not ModelStore.is_pydantic(dtype):
                 dtype = Optional[dtype]  # type: ignore[assignment]
             type_dict[field.name] = dtype
-        return dict_to_data_model(column, type_dict)
+        return dict_to_data_model(f"ArrowDataModel_{column}", type_dict)
     if pa.types.is_map(col_type):
         return dict
     if isinstance(col_type, pa.lib.DictionaryType):

datachain/lib/audio.py

@@ -33,10 +33,14 @@ def audio_info(file: "Union[File, AudioFile]") -> "Audio":
             frames = int(info.num_frames)
             duration = float(frames / sample_rate) if sample_rate > 0 else 0.0
 
-            # Get format information
-            format_name = getattr(info, "format", "")
             codec_name = getattr(info, "encoding", "")
-            bit_rate = getattr(info, "bits_per_sample", 0) * sample_rate * channels
+            file_ext = file.get_file_ext().lower()
+            format_name = _encoding_to_format(codec_name, file_ext)
+
+            bits_per_sample = getattr(info, "bits_per_sample", 0)
+            bit_rate = (
+                bits_per_sample * sample_rate * channels if bits_per_sample > 0 else -1
+            )
 
     except Exception as exc:
         raise FileError(
@@ -54,7 +58,47 @@ def audio_info(file: "Union[File, AudioFile]") -> "Audio":
     )
 
 
-def audio_fragment_np(
+def _encoding_to_format(encoding: str, file_ext: str) -> str:
+    """
+    Map torchaudio encoding to a format name.
+
+    Args:
+        encoding: The encoding string from torchaudio.info()
+        file_ext: The file extension as a fallback
+
+    Returns:
+        Format name as a string
+    """
+    # Direct mapping for formats that match exactly
+    encoding_map = {
+        "FLAC": "flac",
+        "MP3": "mp3",
+        "VORBIS": "ogg",
+        "AMR_WB": "amr",
+        "AMR_NB": "amr",
+        "OPUS": "opus",
+        "GSM": "gsm",
+    }
+
+    if encoding in encoding_map:
+        return encoding_map[encoding]
+
+    # For PCM variants, use file extension to determine format
+    if encoding.startswith("PCM_"):
+        # Common PCM formats by extension
+        pcm_formats = {
+            "wav": "wav",
+            "aiff": "aiff",
+            "au": "au",
+            "raw": "raw",
+        }
+        return pcm_formats.get(file_ext, "wav")  # Default to wav for PCM
+
+    # Fallback to file extension if encoding is unknown
+    return file_ext if file_ext else "unknown"
+
+
+def audio_to_np(
     audio: "AudioFile", start: float = 0, duration: Optional[float] = None
 ) -> "tuple[ndarray, int]":
     """Load audio fragment as numpy array.
@@ -98,14 +142,17 @@ def audio_fragment_np(
         ) from exc
 
 
-def audio_fragment_bytes(
+def audio_to_bytes(
     audio: "AudioFile",
+    format: str = "wav",
     start: float = 0,
     duration: Optional[float] = None,
-    format: str = "wav",
 ) -> bytes:
-    """Convert audio fragment to bytes using soundfile."""
-    y, sr = audio_fragment_np(audio, start, duration)
+    """Convert audio to bytes using soundfile.
+
+    If duration is None, converts from start to end of file.
+    If start is 0 and duration is None, converts entire file."""
+    y, sr = audio_to_np(audio, start, duration)
 
     import io
 
@@ -116,36 +163,82 @@ def audio_fragment_bytes(
     return buffer.getvalue()
 
 
-def save_audio_fragment(
+def save_audio(
     audio: "AudioFile",
-    start: float,
-    end: float,
     output: str,
     format: Optional[str] = None,
+    start: float = 0,
+    end: Optional[float] = None,
 ) -> "AudioFile":
-    """Save audio fragment with timestamped filename.
-    Supports local and remote storage upload."""
-    if start < 0 or end < 0 or start >= end:
-        raise ValueError(f"Invalid time range: ({start:.3f}, {end:.3f})")
-
+    """Save audio file or extract fragment to specified format.
+
+    Args:
+        audio: Source AudioFile object
+        output: Output directory path
+        format: Output format ('wav', 'mp3', etc). Defaults to source format
+        start: Start time in seconds (>= 0). Defaults to 0
+        end: End time in seconds. If None, extracts to end of file
+
+    Returns:
+        AudioFile: New audio file with format conversion/extraction applied
+
+    Examples:
+        save_audio(audio, "/path", "mp3")                       # Entire file to MP3
+        save_audio(audio, "s3://bucket/path", "wav", start=2.5) # From 2.5s to end
+        save_audio(audio, "/path", "flac", start=1, end=3)      # Extract 1-3s fragment
+    """
     if format is None:
         format = audio.get_file_ext()
 
-    duration = end - start
-    start_ms = int(start * 1000)
-    end_ms = int(end * 1000)
-    output_file = posixpath.join(
-        output, f"{audio.get_file_stem()}_{start_ms:06d}_{end_ms:06d}.{format}"
-    )
+    # Validate start time
+    if start < 0:
+        raise ValueError(
+            f"Can't save audio for '{audio.path}', "
+            f"start time must be non-negative: {start:.3f}"
+        )
+
+    # Handle full file conversion when end is None and start is 0
+    if end is None and start == 0:
+        output_file = posixpath.join(output, f"{audio.get_file_stem()}.{format}")
+        try:
+            audio_bytes = audio_to_bytes(audio, format, start=0, duration=None)
+        except Exception as exc:
+            raise FileError(
+                "unable to convert audio file", audio.source, audio.path
+            ) from exc
+    elif end is None:
+        # Extract from start to end of file
+        output_file = posixpath.join(
+            output, f"{audio.get_file_stem()}_{int(start * 1000):06d}_end.{format}"
+        )
+        try:
+            audio_bytes = audio_to_bytes(audio, format, start=start, duration=None)
+        except Exception as exc:
+            raise FileError(
+                "unable to save audio fragment", audio.source, audio.path
+            ) from exc
+    else:
+        # Fragment extraction mode with specific end time
+        if end < 0 or start >= end:
+            raise ValueError(
+                f"Can't save audio for '{audio.path}', "
+                f"invalid time range: ({start:.3f}, {end:.3f})"
+            )
 
-    try:
-        audio_bytes = audio_fragment_bytes(audio, start, duration, format)
+        duration = end - start
+        start_ms = int(start * 1000)
+        end_ms = int(end * 1000)
+        output_file = posixpath.join(
+            output, f"{audio.get_file_stem()}_{start_ms:06d}_{end_ms:06d}.{format}"
+        )
 
-        from datachain.lib.file import AudioFile
+        try:
+            audio_bytes = audio_to_bytes(audio, format, start, duration)
+        except Exception as exc:
+            raise FileError(
+                "unable to save audio fragment", audio.source, audio.path
+            ) from exc
 
-        return AudioFile.upload(audio_bytes, output_file, catalog=audio._catalog)
+    from datachain.lib.file import AudioFile
 
-    except Exception as exc:
-        raise FileError(
-            "unable to save audio fragment", audio.source, audio.path
-        ) from exc
+    return AudioFile.upload(audio_bytes, output_file, catalog=audio._catalog)

datachain/lib/data_model.py

@@ -1,3 +1,5 @@
+import inspect
+import uuid
 from collections.abc import Sequence
 from datetime import datetime
 from typing import ClassVar, Optional, Union, get_args, get_origin
@@ -80,7 +82,9 @@ def dict_to_data_model(
 
     fields = {
         name: (
-            anno,
+            anno
+            if inspect.isclass(anno) and issubclass(anno, BaseModel)
+            else Optional[anno],
             Field(
                 validation_alias=AliasChoices(name, original_names[idx] or name),
                 default=None,
@@ -101,6 +105,10 @@ def dict_to_data_model(
                     field_info[str(alias)] = (_name, field)
             return field_info
 
+    # Generate random unique name if not provided
+    if not name:
+        name = f"DataModel_{uuid.uuid4().hex[:8]}"
+
     return create_model(
         name,
         __base__=_DataModelStrict,

datachain/lib/dc/datachain.py

@@ -2388,7 +2388,7 @@ class DataChain:
         placement: FileExportPlacement = "fullpath",
         link_type: Literal["copy", "symlink"] = "copy",
         num_threads: Optional[int] = EXPORT_FILES_MAX_THREADS,
-        anon: bool = False,
+        anon: Optional[bool] = None,
         client_config: Optional[dict] = None,
     ) -> None:
         """Export files from a specified signal to a directory. Files can be
@@ -2403,7 +2403,11 @@ class DataChain:
                 Falls back to `'copy'` if symlinking fails.
             num_threads : number of threads to use for exporting files.
                 By default it uses 5 threads.
-            anon: If true, we will treat cloud bucket as public one
+            anon: If True, we will treat cloud bucket as public one. Default behavior
+                depends on the previous session configuration (e.g. happens in the
+                initial `read_storage`) and particular cloud storage client
+                implementation (e.g. S3 fallbacks to anonymous access if no credentials
+                were found).
             client_config: Optional configuration for the destination storage client
 
         Example:
@@ -2421,8 +2425,8 @@ class DataChain:
         ):
             raise ValueError("Files with the same name found")
 
-        if anon:
-            client_config = (client_config or {}) | {"anon": True}
+        if anon is not None:
+            client_config = (client_config or {}) | {"anon": anon}
 
         progress_bar = tqdm(
             desc=f"Exporting files to {output}: ",

datachain/lib/dc/hf.py

@@ -25,19 +25,23 @@ def read_hf(
     settings: Optional[dict] = None,
     column: str = "",
     model_name: str = "",
+    limit: int = 0,
     **kwargs,
 ) -> "DataChain":
-    """Generate chain from huggingface hub dataset.
+    """Generate chain from Hugging Face Hub dataset.
 
     Parameters:
         dataset : Path or name of the dataset to read from Hugging Face Hub,
             or an instance of `datasets.Dataset`-like object.
-        args : Additional positional arguments to pass to datasets.load_dataset.
+        args : Additional positional arguments to pass to `datasets.load_dataset`.
         session : Session to use for the chain.
         settings : Settings to use for the chain.
         column : Generated object column name.
         model_name : Generated model name.
-        kwargs : Parameters to pass to datasets.load_dataset.
+        limit : Limit the number of items to read from the HF dataset.
+                Adds `take(limit)` to the `datasets.load_dataset`.
+                Defaults to 0 (no limit).
+        kwargs : Parameters to pass to `datasets.load_dataset`.
 
     Example:
         Load from Hugging Face Hub:
@@ -53,6 +57,18 @@ def read_hf(
         import datachain as dc
         chain = dc.read_hf(ds)
         ```
+
+        Streaming with limit, for large datasets:
+        ```py
+        import datachain as dc
+        ds = dc.read_hf("beans", split="train", streaming=True, limit=10)
+        ```
+
+        or use HF split syntax (not supported if streaming is enabled):
+        ```py
+        import datachain as dc
+        ds = dc.read_hf("beans", split="train[%10]")
+        ```
     """
     from datachain.lib.hf import HFGenerator, get_output_schema, stream_splits
 
@@ -72,4 +88,4 @@ def read_hf(
         output = {column: model}
 
     chain = read_values(split=list(ds_dict.keys()), session=session, settings=settings)
-    return chain.gen(HFGenerator(dataset, model, *args, **kwargs), output=output)
+    return chain.gen(HFGenerator(dataset, model, limit, *args, **kwargs), output=output)

datachain/lib/dc/storage.py

@@ -33,7 +33,7 @@ def read_storage(
     recursive: Optional[bool] = True,
     column: str = "file",
     update: bool = False,
-    anon: bool = False,
+    anon: Optional[bool] = None,
     delta: Optional[bool] = False,
     delta_on: Optional[Union[str, Sequence[str]]] = (
         "file.path",
@@ -124,8 +124,8 @@ def read_storage(
 
     file_type = get_file_type(type)
 
-    if anon:
-        client_config = (client_config or {}) | {"anon": True}
+    if anon is not None:
+        client_config = (client_config or {}) | {"anon": anon}
     session = Session.get(session, client_config=client_config, in_memory=in_memory)
     catalog = session.catalog
     cache = catalog.cache

datachain/lib/file.py

@@ -717,6 +717,23 @@ class ImageFile(File):
         destination = stringify_path(destination)
 
         client: Client = self._catalog.get_client(destination, **(client_config or {}))
+
+        # If format is not provided, determine it from the file extension
+        if format is None:
+            from pathlib import PurePosixPath
+
+            from PIL import Image as PilImage
+
+            ext = PurePosixPath(destination).suffix.lower()
+            format = PilImage.registered_extensions().get(ext)
+
+        if not format:
+            raise FileError(
+                f"Can't determine format for destination '{destination}'",
+                self.source,
+                self.path,
+            )
+
         with client.fs.open(destination, mode="wb") as f:
             self.read().save(f, format=format)
 
@@ -815,7 +832,10 @@ class VideoFile(File):
             VideoFragment: A Model representing the video fragment.
         """
         if start < 0 or end < 0 or start >= end:
-            raise ValueError(f"Invalid time range: ({start:.3f}, {end:.3f})")
+            raise ValueError(
+                f"Can't get video fragment for '{self.path}', "
+                f"invalid time range: ({start:.3f}, {end:.3f})"
+            )
 
         return VideoFragment(video=self, start=start, end=end)
 
@@ -898,7 +918,10 @@ class AudioFile(File):
             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})")
+            raise ValueError(
+                f"Can't get audio fragment for '{self.path}', "
+                f"invalid time range: ({start:.3f}, {end:.3f})"
+            )
 
         return AudioFragment(audio=self, start=start, end=end)
 
@@ -941,6 +964,35 @@ class AudioFile(File):
             yield self.get_fragment(start, min(start + duration, end))
             start += duration
 
+    def save(  # type: ignore[override]
+        self,
+        output: str,
+        format: Optional[str] = None,
+        start: float = 0,
+        end: Optional[float] = None,
+        client_config: Optional[dict] = None,
+    ) -> "AudioFile":
+        """Save audio file or extract fragment to specified format.
+
+        Args:
+            output: Output directory path
+            format: Output format ('wav', 'mp3', etc). Defaults to source format
+            start: Start time in seconds (>= 0). Defaults to 0
+            end: End time in seconds. If None, extracts to end of file
+            client_config: Optional client configuration
+
+        Returns:
+            AudioFile: New audio file with format conversion/extraction applied
+
+        Examples:
+            audio.save("/path", "mp3")                        # Entire file to MP3
+            audio.save("s3://bucket/path", "wav", start=2.5)  # From 2.5s to end as WAV
+            audio.save("/path", "flac", start=1, end=3)       # 1-3s fragment as FLAC
+        """
+        from .audio import save_audio
+
+        return save_audio(self, output, format, start, end)
+
 
 class AudioFragment(DataModel):
     """
@@ -968,10 +1020,10 @@ class AudioFragment(DataModel):
             tuple[ndarray, int]: A tuple containing the audio data as a NumPy array
                                and the sample rate.
         """
-        from .audio import audio_fragment_np
+        from .audio import audio_to_np
 
         duration = self.end - self.start
-        return audio_fragment_np(self.audio, self.start, duration)
+        return audio_to_np(self.audio, self.start, duration)
 
     def read_bytes(self, format: str = "wav") -> bytes:
         """
@@ -984,10 +1036,10 @@ class AudioFragment(DataModel):
         Returns:
             bytes: The encoded audio fragment as bytes.
         """
-        from .audio import audio_fragment_bytes
+        from .audio import audio_to_bytes
 
         duration = self.end - self.start
-        return audio_fragment_bytes(self.audio, self.start, duration, format)
+        return audio_to_bytes(self.audio, format, self.start, duration)
 
     def save(self, output: str, format: Optional[str] = None) -> "AudioFile":
         """
@@ -1005,9 +1057,9 @@ class AudioFragment(DataModel):
         Returns:
             AudioFile: A Model representing the saved audio file.
         """
-        from .audio import save_audio_fragment
+        from .audio import save_audio
 
-        return save_audio_fragment(self.audio, self.start, self.end, output, format)
+        return save_audio(self.audio, output, format, self.start, self.end)
 
 
 class VideoFrame(DataModel):

datachain/lib/hf.py

@@ -69,21 +69,25 @@ class HFGenerator(Generator):
         self,
         ds: Union[str, HFDatasetType],
         output_schema: type["BaseModel"],
+        limit: int = 0,
         *args,
         **kwargs,
     ):
         """
-        Generator for chain from huggingface datasets.
+        Generator for chain from Hugging Face datasets.
 
         Parameters:
 
-        ds : Path or name of the dataset to read from Hugging Face Hub,
-            or an instance of `datasets.Dataset`-like object.
-        output_schema : Pydantic model for validation.
+            ds : Path or name of the dataset to read from Hugging Face Hub,
+                or an instance of `datasets.Dataset`-like object.
+            limit : Limit the number of items to read from the HF dataset.
+                    Defaults to 0 (no limit).
+            output_schema : Pydantic model for validation.
         """
         super().__init__()
         self.ds = ds
         self.output_schema = output_schema
+        self.limit = limit
         self.args = args
         self.kwargs = kwargs
 
@@ -93,6 +97,8 @@ class HFGenerator(Generator):
     def process(self, split: str = ""):
         desc = "Parsed Hugging Face dataset"
         ds = self.ds_dict[split]
+        if self.limit > 0:
+            ds = ds.take(self.limit)
         if split:
             desc += f" split '{split}'"
         model_fields = self.output_schema._model_fields_by_aliases()  # type: ignore[attr-defined]
@@ -113,7 +119,6 @@ class HFGenerator(Generator):
 
 def stream_splits(ds: Union[str, HFDatasetType], *args, **kwargs):
     if isinstance(ds, str):
-        kwargs["streaming"] = True
         ds = load_dataset(ds, *args, **kwargs)
     if isinstance(ds, (DatasetDict, IterableDatasetDict)):
         return ds
@@ -132,7 +137,12 @@ def convert_feature(val: Any, feat: Any, anno: Any) -> Any:
             sfeat = feat[sname]
             norm_name, info = model_fields[sname]
             sanno = info.annotation
-            sdict[norm_name] = [convert_feature(v, sfeat, sanno) for v in val[sname]]
+            if isinstance(val[sname], list):
+                sdict[norm_name] = [
+                    convert_feature(v, sfeat, sanno) for v in val[sname]
+                ]
+            else:
+                sdict[norm_name] = convert_feature(val[sname], sfeat, sanno)
         return anno(**sdict)
     if isinstance(feat, Image):
         if isinstance(val, dict):
@@ -174,7 +184,7 @@ def _feature_to_chain_type(name: str, val: Any) -> DataType:  # noqa: PLR0911
         for sname, sval in val.items():
             dtype = _feature_to_chain_type(sname, sval)
             sequence_dict[sname] = dtype  # type: ignore[valid-type]
-        return dict_to_data_model(name, sequence_dict)  # type: ignore[arg-type]
+        return dict_to_data_model(f"HFDataModel_{name}", sequence_dict)  # type: ignore[arg-type]
     if isinstance(val, List):
         return list[_feature_to_chain_type(name, val.feature)]  # type: ignore[arg-type,misc,return-value]
     if isinstance(val, Array2D):

datachain/lib/video.py

@@ -205,7 +205,10 @@ def save_video_fragment(
         VideoFile: Video fragment model.
     """
     if start < 0 or end < 0 or start >= end:
-        raise ValueError(f"Invalid time range: ({start:.3f}, {end:.3f})")
+        raise ValueError(
+            f"Can't save video fragment for '{video.path}', "
+            f"invalid time range: ({start:.3f}, {end:.3f})"
+        )
 
     if format is None:
         format = video.get_file_ext()

datachain/remote/studio.py

@@ -429,6 +429,8 @@ class StudioClient:
         repository: Optional[str] = None,
         priority: Optional[int] = None,
         cluster: Optional[str] = None,
+        start_time: Optional[str] = None,
+        cron: Optional[str] = None,
     ) -> Response[JobData]:
         data = {
             "query": query,
@@ -442,6 +444,8 @@ class StudioClient:
             "repository": repository,
             "priority": priority,
             "compute_cluster_name": cluster,
+            "start_after": start_time,
+            "cron_expression": cron,
         }
         return self._send_request("datachain/job", data)
 

datachain/studio.py

@@ -1,8 +1,10 @@
 import asyncio
 import os
 import sys
+from datetime import datetime, timezone
 from typing import TYPE_CHECKING, Optional
 
+import dateparser
 import tabulate
 
 from datachain.config import Config, ConfigLevel
@@ -42,6 +44,8 @@ def process_jobs_args(args: "Namespace"):
             args.req_file,
             args.priority,
             args.cluster,
+            args.start_time,
+            args.cron,
         )
 
     if args.cmd == "cancel":
@@ -262,6 +266,24 @@ def save_config(hostname, token, level=ConfigLevel.GLOBAL):
     return config.config_file()
 
 
+def parse_start_time(start_time_str: Optional[str]) -> Optional[str]:
+    if not start_time_str:
+        return None
+
+    # Parse the datetime string using dateparser
+    parsed_datetime = dateparser.parse(start_time_str)
+
+    if parsed_datetime is None:
+        raise DataChainError(
+            f"Could not parse datetime string: '{start_time_str}'. "
+            f"Supported formats include: '2024-01-15 14:30:00', 'tomorrow 3pm', "
+            f"'monday 9am', '2024-01-15T14:30:00Z', 'in 2 hours', etc."
+        )
+
+    # Convert to ISO format string
+    return parsed_datetime.isoformat()
+
+
 def show_logs_from_client(client, job_id):
     # Sync usage
     async def _run():
@@ -310,6 +332,8 @@ def create_job(
     req_file: Optional[str] = None,
     priority: Optional[int] = None,
     cluster: Optional[str] = None,
+    start_time: Optional[str] = None,
+    cron: Optional[str] = None,
 ):
     query_type = "PYTHON" if query_file.endswith(".py") else "SHELL"
     with open(query_file) as f:
@@ -328,6 +352,11 @@ def create_job(
     client = StudioClient(team=team_name)
     file_ids = upload_files(client, files) if files else []
 
+    # Parse start_time if provided
+    parsed_start_time = parse_start_time(start_time)
+    if cron and parsed_start_time is None:
+        parsed_start_time = datetime.now(timezone.utc).isoformat()
+
     response = client.create_job(
         query=query,
         query_type=query_type,
@@ -340,6 +369,8 @@ def create_job(
         requirements=requirements,
         priority=priority,
         cluster=cluster,
+        start_time=parsed_start_time,
+        cron=cron,
     )
     if not response.ok:
         raise DataChainError(response.message)
@@ -348,6 +379,11 @@ def create_job(
         raise DataChainError("Failed to create job")
 
     job_id = response.data.get("job", {}).get("id")
+
+    if parsed_start_time or cron:
+        print(f"Job {job_id} is scheduled as a task in Studio.")
+        return 0
+
     print(f"Job {job_id} created")
     print("Open the job in Studio at", response.data.get("job", {}).get("url"))
     print("=" * 40)

{datachain-0.26.3.dist-info → datachain-0.27.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.26.3
+Version: 0.27.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -26,6 +26,7 @@ Requires-Dist: packaging
 Requires-Dist: pyarrow
 Requires-Dist: typing-extensions
 Requires-Dist: python-dateutil>=2
+Requires-Dist: dateparser>=1.0.0
 Requires-Dist: attrs>=21.3.0
 Requires-Dist: fsspec>=2024.2.0
 Requires-Dist: s3fs>=2024.2.0
@@ -100,6 +101,7 @@ Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
 Requires-Dist: mypy==1.17.0; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
+Requires-Dist: types-dateparser; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-requests; extra == "dev"
@@ -118,7 +120,7 @@ Dynamic: license-file
 |logo| DataChain
 ================
 
-|PyPI| |Python Version| |Codecov| |Tests|
+|PyPI| |Python Version| |Codecov| |Tests| |DeepWiki|
 
 .. |logo| image:: docs/assets/datachain.svg
    :height: 24
@@ -134,6 +136,9 @@ Dynamic: license-file
 .. |Tests| image:: https://github.com/iterative/datachain/actions/workflows/tests.yml/badge.svg
    :target: https://github.com/iterative/datachain/actions/workflows/tests.yml
    :alt: Tests
+.. |DeepWiki| image:: https://deepwiki.com/badge.svg
+   :target: https://deepwiki.com/iterative/datachain
+   :alt: DeepWiki
 
 DataChain is a Python-based AI-data warehouse for transforming and analyzing unstructured
 data like images, audio, videos, text and PDFs. It integrates with external storage

{datachain-0.26.3.dist-info → datachain-0.27.0.dist-info}/RECORD

@@ -17,7 +17,7 @@ datachain/project.py,sha256=90D4GpJSA3t0fayYZbzrL3sk4U7EJhQo8psnWvdI7_o,2280
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/script_meta.py,sha256=V-LaFOZG84pD0Zc0NvejYdzwDgzITv6yHvAHggDCnuY,4978
 datachain/semver.py,sha256=UB8GHPBtAP3UJGeiuJoInD7SK-DnB93_Xd1qy_CQ9cU,2074
-datachain/studio.py,sha256=bLok-eJNFRHQScEyAyA_Fas52dmijd5r-73KudWxV4k,13337
+datachain/studio.py,sha256=RCpVZdHRX-ClEddXaAsZDGFy5o-SOqVCa5NhLj8337s,14486
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=DNqOi-Ydb7InyWvD9m7_yailxz6-YGpZzh00biQaHNo,15305
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
@@ -35,7 +35,7 @@ datachain/cli/commands/misc.py,sha256=c0DmkOLwcDI2YhA8ArOuLJk6aGzSMZCiKL_E2JGibV
 datachain/cli/commands/query.py,sha256=Xzfgh14nPVH-sclqX1tpZqgfdTugw5s_44v0D33z6FA,1505
 datachain/cli/commands/show.py,sha256=Cf8wBs12h-xtdOzjU5GTDy2C8rF5HJSF0hDJYER1zH8,1606
 datachain/cli/parser/__init__.py,sha256=NPB6ssP4CCt7G1SWZ_8oNQEH2C1lktWgkyHYXDQJZNc,15073
-datachain/cli/parser/job.py,sha256=_wqOOxGRXG_-xuQ35FaLUOwjw6w8HviWvoEpZZ7VBzI,5289
+datachain/cli/parser/job.py,sha256=iytBZaCcQUhaOcRlYZFeAJsscN2T2XcEY7MibTeuZhg,5786
 datachain/cli/parser/studio.py,sha256=Bo__LKM7qhJGgkyX8M_bCvgZ2Gvqq6r_X4t1NdtaBIY,3881
 datachain/cli/parser/utils.py,sha256=rETdD-9Hq9A4OolgfT7jQw4aoawtbfmkdtH6E7nkhpI,2888
 datachain/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,49
@@ -70,13 +70,13 @@ datachain/func/random.py,sha256=t7jwXsI8-hy0qAdvjAntgzy-AHtTAfozlZ1CpKR-QZE,458
 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=gMgmiMOhTGFMSyWBbjyzF2RsSXjx0XmUGPoSBxcWwe0,10756
-datachain/lib/audio.py,sha256=J7XJ14ItPF9y6pN-tmMV9In9X9rgwlBwzyzdGOUkPGk,4376
+datachain/lib/arrow.py,sha256=geoLvyDd5uMqS3D9Ec1ODlShCUAdtwHUwl8FqbUX_hg,10776
+datachain/lib/audio.py,sha256=fQmIBq-9hrUZtkgeJdPHYA_D8Wfe9D4cQZk4_ijxpNc,7580
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
-datachain/lib/data_model.py,sha256=JPHPO6z-pehyiY-qNBAnp8u015xUHrijPKbGkMHS6lo,3493
+datachain/lib/data_model.py,sha256=Rjah76GHwIV6AZQk4rsdg6JLre5D8Kb9T4PS5SXzsPA,3740
 datachain/lib/dataset_info.py,sha256=7w-DoKOyIVoOtWGCgciMLcP5CiAWJB3rVI-vUDF80k0,3311
-datachain/lib/file.py,sha256=tHBBacsh1580UPFC6fAINBNwNiyymNgzj89rpsz1LKc,40817
-datachain/lib/hf.py,sha256=dadHs2dsi4ALwXz92Y3T7AUgq3wQF4mBydWqHCMjvks,6880
+datachain/lib/file.py,sha256=_ch7xYcpl0kzImgEwccbQ-a5qb9rbEvx1vcuWerOn9k,42608
+datachain/lib/hf.py,sha256=3xdvPQPilnJiGv3H4S4bTGqvrGGlZgZmqjE1n_SMJZg,7293
 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
@@ -92,7 +92,7 @@ datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
 datachain/lib/udf.py,sha256=SUnJWRDC3TlLhvpi8iqqJbeZGn5DChot7DyH-0Q-z20,17305
 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
+datachain/lib/video.py,sha256=ddVstiMkfxyBPDsnjCKY0d_93bw-DcMqGqN60yzsZoo,6851
 datachain/lib/webdataset.py,sha256=CkW8FfGigNx6wo2EEK4KMjhEE8FamRHWGs2HZuH7jDY,7214
 datachain/lib/webdataset_laion.py,sha256=xvT6m_r5y0KbOx14BUe7UC5mOgrktJq53Mh-H0EVlUE,2525
 datachain/lib/convert/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -104,15 +104,15 @@ datachain/lib/convert/values_to_tuples.py,sha256=j5yZMrVUH6W7b-7yUvdCTGI7JCUAYUO
 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=ap54lcuj71tvp0zX1jiFFiEWvA5UPeyYJRJkd2APmlI,92897
+datachain/lib/dc/datachain.py,sha256=mLE5v4KhzEQm7HVWBTxY6EwJ2J-YeFVcLUY4I21216c,93212
 datachain/lib/dc/datasets.py,sha256=P6CIJizD2IYFwOQG5D3VbQRjDmUiRH0ysdtb551Xdm8,15098
-datachain/lib/dc/hf.py,sha256=MJWO-NL4jAD6CEAmXsyeqXEyvefRLMhyxhT9jKT5vMU,2324
+datachain/lib/dc/hf.py,sha256=AP_MUHg6HJWae10PN9hD_beQVjrl0cleZ6Cvhtl1yoI,2901
 datachain/lib/dc/json.py,sha256=dNijfJ-H92vU3soyR7X1IiDrWhm6yZIGG3bSnZkPdAE,2733
 datachain/lib/dc/listings.py,sha256=V379Cb-7ZyquM0w7sWArQZkzInZy4GB7QQ1ZfowKzQY,4544
 datachain/lib/dc/pandas.py,sha256=ObueUXDUFKJGu380GmazdG02ARpKAHPhSaymfmOH13E,1489
 datachain/lib/dc/parquet.py,sha256=zYcSgrWwyEDW9UxGUSVdIVsCu15IGEf0xL8KfWQqK94,1782
 datachain/lib/dc/records.py,sha256=FpPbApWopUri1gIaSMsfXN4fevja4mjmfb6Q5eiaGxI,3116
-datachain/lib/dc/storage.py,sha256=8xiV3c6k-sG14RGwNJCp0AbV6L0mNDsTVZ-Est-ccnw,7672
+datachain/lib/dc/storage.py,sha256=FXroEdxOZfbuEBIWfWTkbGwrI0D4_mrLZSRsIQm0WFE,7693
 datachain/lib/dc/utils.py,sha256=VawOAlJSvAtZbsMg33s5tJe21TRx1Km3QggI1nN6tnw,3984
 datachain/lib/dc/values.py,sha256=7l1n352xWrEdql2NhBcZ3hj8xyPglWiY4qHjFPjn6iw,1428
 datachain/model/__init__.py,sha256=R9faX5OHV1xh2EW-g2MPedwbtEqt3LodJRyluB-QylI,189
@@ -136,7 +136,7 @@ datachain/query/session.py,sha256=gKblltJAVQAVSTswAgWGDgGbpmFlFzFVkIQojDCjgXM,68
 datachain/query/udf.py,sha256=e753bDJzTNjGFQn1WGTvOAWSwjDbrFI1-_DDWkWN2ls,1343
 datachain/query/utils.py,sha256=HaSDNH_XGvp_NIcXjcB7j4vJRPi4_tbztDWclYelHY4,1208
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/remote/studio.py,sha256=oJp2KD9eO8zQDnPfNpAALZYsOlBfqVKKRTeCkEpcsYk,15196
+datachain/remote/studio.py,sha256=vsuqCAO65PBJKGLMxOvc3Bmieo2TJwcfc9YclxkzmFk,15350
 datachain/sql/__init__.py,sha256=6SQRdbljO3d2hx3EAVXEZrHQKv5jth0Jh98PogT59No,262
 datachain/sql/selectable.py,sha256=cTc60qVoAwqqss0Vop8Lt5Z-ROnM1XrQmL_GLjRxhXs,1765
 datachain/sql/types.py,sha256=ASSPkmM5EzdRindqj2O7WHLXq8VHAgFYedG8lYfGvVI,14045
@@ -158,9 +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-0.26.3.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.26.3.dist-info/METADATA,sha256=HdG_quEq0rfrdKJJ_teSViVCXbXI3SxLlnh6tu2Mgfs,13543
-datachain-0.26.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.26.3.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.26.3.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.26.3.dist-info/RECORD,,
+datachain-0.27.0.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.27.0.dist-info/METADATA,sha256=PWZ_EWTpk1OvWlQZe__5SCjFem6BD1AtYmTxJ5wV3iY,13759
+datachain-0.27.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.27.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.27.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.27.0.dist-info/RECORD,,