datachain 0.8.4__py3-none-any.whl → 0.8.5__py3-none-any.whl

datachain/query/dataset.py

@@ -35,6 +35,7 @@ from sqlalchemy.sql.schema import TableClause
 from sqlalchemy.sql.selectable import Select
 
 from datachain.asyn import ASYNC_WORKERS, AsyncMapper, OrderedMapper
+from datachain.catalog.catalog import clone_catalog_with_cache
 from datachain.data_storage.schema import (
     PARTITION_COLUMN_ID,
     partition_col_names,
@@ -43,7 +44,8 @@ from datachain.data_storage.schema import (
 from datachain.dataset import DatasetStatus, RowDict
 from datachain.error import DatasetNotFoundError, QueryScriptCancelError
 from datachain.func.base import Function
-from datachain.progress import CombinedDownloadCallback
+from datachain.lib.udf import UDFAdapter, _get_cache
+from datachain.progress import CombinedDownloadCallback, TqdmCombinedDownloadCallback
 from datachain.query.schema import C, UDFParamSpec, normalize_param
 from datachain.query.session import Session
 from datachain.sql.functions.random import rand
@@ -52,6 +54,7 @@ from datachain.utils import (
     determine_processes,
     filtered_cloudpickle_dumps,
     get_datachain_executable,
+    safe_closing,
 )
 
 if TYPE_CHECKING:
@@ -349,19 +352,26 @@ def process_udf_outputs(
     warehouse.insert_rows_done(udf_table)
 
 
-def get_download_callback() -> Callback:
-    return CombinedDownloadCallback(
-        {"desc": "Download", "unit": "B", "unit_scale": True, "unit_divisor": 1024}
+def get_download_callback(suffix: str = "", **kwargs) -> CombinedDownloadCallback:
+    return TqdmCombinedDownloadCallback(
+        {
+            "desc": "Download" + suffix,
+            "unit": "B",
+            "unit_scale": True,
+            "unit_divisor": 1024,
+            "leave": False,
+            **kwargs,
+        },
     )
 
 
 def get_processed_callback() -> Callback:
-    return TqdmCallback({"desc": "Processed", "unit": " rows"})
+    return TqdmCallback({"desc": "Processed", "unit": " rows", "leave": False})
 
 
 def get_generated_callback(is_generator: bool = False) -> Callback:
     if is_generator:
-        return TqdmCallback({"desc": "Generated", "unit": " rows"})
+        return TqdmCallback({"desc": "Generated", "unit": " rows", "leave": False})
     return DEFAULT_CALLBACK
 
 
@@ -412,97 +422,109 @@ class UDFStep(Step, ABC):
 
         udf_fields = [str(c.name) for c in query.selected_columns]
 
-        try:
-            if workers:
-                if self.catalog.in_memory:
-                    raise RuntimeError(
-                        "In-memory databases cannot be used with "
-                        "distributed processing."
-                    )
+        prefetch = self.udf.prefetch
+        with _get_cache(self.catalog.cache, prefetch, use_cache=self.cache) as _cache:
+            catalog = clone_catalog_with_cache(self.catalog, _cache)
+            try:
+                if workers:
+                    if catalog.in_memory:
+                        raise RuntimeError(
+                            "In-memory databases cannot be used with "
+                            "distributed processing."
+                        )
 
-                from datachain.catalog.loader import get_distributed_class
-
-                distributor = get_distributed_class(min_task_size=self.min_task_size)
-                distributor(
-                    self.udf,
-                    self.catalog,
-                    udf_table,
-                    query,
-                    workers,
-                    processes,
-                    udf_fields=udf_fields,
-                    is_generator=self.is_generator,
-                    use_partitioning=use_partitioning,
-                    cache=self.cache,
-                )
-            elif processes:
-                # Parallel processing (faster for more CPU-heavy UDFs)
-                if self.catalog.in_memory:
-                    raise RuntimeError(
-                        "In-memory databases cannot be used with parallel processing."
-                    )
-                udf_info: UdfInfo = {
-                    "udf_data": filtered_cloudpickle_dumps(self.udf),
-                    "catalog_init": self.catalog.get_init_params(),
-                    "metastore_clone_params": self.catalog.metastore.clone_params(),
-                    "warehouse_clone_params": self.catalog.warehouse.clone_params(),
-                    "table": udf_table,
-                    "query": query,
-                    "udf_fields": udf_fields,
-                    "batching": batching,
-                    "processes": processes,
-                    "is_generator": self.is_generator,
-                    "cache": self.cache,
-                }
-
-                # Run the UDFDispatcher in another process to avoid needing
-                # if __name__ == '__main__': in user scripts
-                exec_cmd = get_datachain_executable()
-                cmd = [*exec_cmd, "internal-run-udf"]
-                envs = dict(os.environ)
-                envs.update({"PYTHONPATH": os.getcwd()})
-                process_data = filtered_cloudpickle_dumps(udf_info)
-
-                with subprocess.Popen(cmd, env=envs, stdin=subprocess.PIPE) as process:  # noqa: S603
-                    process.communicate(process_data)
-                    if retval := process.poll():
-                        raise RuntimeError(f"UDF Execution Failed! Exit code: {retval}")
-            else:
-                # Otherwise process single-threaded (faster for smaller UDFs)
-                warehouse = self.catalog.warehouse
-
-                udf_inputs = batching(warehouse.dataset_select_paginated, query)
-                download_cb = get_download_callback()
-                processed_cb = get_processed_callback()
-                generated_cb = get_generated_callback(self.is_generator)
-                try:
-                    udf_results = self.udf.run(
-                        udf_fields,
-                        udf_inputs,
-                        self.catalog,
-                        self.cache,
-                        download_cb,
-                        processed_cb,
+                    from datachain.catalog.loader import get_distributed_class
+
+                    distributor = get_distributed_class(
+                        min_task_size=self.min_task_size
                     )
-                    process_udf_outputs(
-                        warehouse,
-                        udf_table,
-                        udf_results,
+                    distributor(
                         self.udf,
-                        cb=generated_cb,
+                        catalog,
+                        udf_table,
+                        query,
+                        workers,
+                        processes,
+                        udf_fields=udf_fields,
+                        is_generator=self.is_generator,
+                        use_partitioning=use_partitioning,
+                        cache=self.cache,
                     )
-                finally:
-                    download_cb.close()
-                    processed_cb.close()
-                    generated_cb.close()
-
-        except QueryScriptCancelError:
-            self.catalog.warehouse.close()
-            sys.exit(QUERY_SCRIPT_CANCELED_EXIT_CODE)
-        except (Exception, KeyboardInterrupt):
-            # Close any open database connections if an error is encountered
-            self.catalog.warehouse.close()
-            raise
+                elif processes:
+                    # Parallel processing (faster for more CPU-heavy UDFs)
+                    if catalog.in_memory:
+                        raise RuntimeError(
+                            "In-memory databases cannot be used "
+                            "with parallel processing."
+                        )
+                    udf_info: UdfInfo = {
+                        "udf_data": filtered_cloudpickle_dumps(self.udf),
+                        "catalog_init": catalog.get_init_params(),
+                        "metastore_clone_params": catalog.metastore.clone_params(),
+                        "warehouse_clone_params": catalog.warehouse.clone_params(),
+                        "table": udf_table,
+                        "query": query,
+                        "udf_fields": udf_fields,
+                        "batching": batching,
+                        "processes": processes,
+                        "is_generator": self.is_generator,
+                        "cache": self.cache,
+                    }
+
+                    # Run the UDFDispatcher in another process to avoid needing
+                    # if __name__ == '__main__': in user scripts
+                    exec_cmd = get_datachain_executable()
+                    cmd = [*exec_cmd, "internal-run-udf"]
+                    envs = dict(os.environ)
+                    envs.update({"PYTHONPATH": os.getcwd()})
+                    process_data = filtered_cloudpickle_dumps(udf_info)
+
+                    with subprocess.Popen(  # noqa: S603
+                        cmd, env=envs, stdin=subprocess.PIPE
+                    ) as process:
+                        process.communicate(process_data)
+                        if retval := process.poll():
+                            raise RuntimeError(
+                                f"UDF Execution Failed! Exit code: {retval}"
+                            )
+                else:
+                    # Otherwise process single-threaded (faster for smaller UDFs)
+                    warehouse = catalog.warehouse
+
+                    udf_inputs = batching(warehouse.dataset_select_paginated, query)
+                    download_cb = get_download_callback()
+                    processed_cb = get_processed_callback()
+                    generated_cb = get_generated_callback(self.is_generator)
+
+                    try:
+                        udf_results = self.udf.run(
+                            udf_fields,
+                            udf_inputs,
+                            catalog,
+                            self.cache,
+                            download_cb,
+                            processed_cb,
+                        )
+                        with safe_closing(udf_results):
+                            process_udf_outputs(
+                                warehouse,
+                                udf_table,
+                                udf_results,
+                                self.udf,
+                                cb=generated_cb,
+                            )
+                    finally:
+                        download_cb.close()
+                        processed_cb.close()
+                        generated_cb.close()
+
+            except QueryScriptCancelError:
+                self.catalog.warehouse.close()
+                sys.exit(QUERY_SCRIPT_CANCELED_EXIT_CODE)
+            except (Exception, KeyboardInterrupt):
+                # Close any open database connections if an error is encountered
+                self.catalog.warehouse.close()
+                raise
 
     def create_partitions_table(self, query: Select) -> "Table":
         """
@@ -602,6 +624,13 @@ class UDFSignal(UDFStep):
         signal_name_cols = {c.name: c for c in signal_cols}
         cols = signal_cols
 
+        overlap = {c.name for c in original_cols} & {c.name for c in cols}
+        if overlap:
+            raise ValueError(
+                "Column already exists or added in the previous steps: "
+                + ", ".join(overlap)
+            )
+
         def q(*columns):
             cols1 = []
             cols2 = []

datachain/query/dispatch.py

@@ -14,7 +14,9 @@ from multiprocess import get_context
 from sqlalchemy.sql import func
 
 from datachain.catalog import Catalog
+from datachain.catalog.catalog import clone_catalog_with_cache
 from datachain.catalog.loader import get_distributed_class
+from datachain.lib.udf import _get_cache
 from datachain.query.batch import RowsOutput, RowsOutputBatch
 from datachain.query.dataset import (
     get_download_callback,
@@ -25,7 +27,7 @@ from datachain.query.dataset import (
 from datachain.query.queue import get_from_queue, put_into_queue
 from datachain.query.udf import UdfInfo
 from datachain.query.utils import get_query_id_column
-from datachain.utils import batched, flatten
+from datachain.utils import batched, flatten, safe_closing
 
 if TYPE_CHECKING:
     from sqlalchemy import Select, Table
@@ -304,21 +306,25 @@ class UDFWorker:
         processed_cb = ProcessedCallback()
         generated_cb = get_generated_callback(self.is_generator)
 
-        udf_results = self.udf.run(
-            self.udf_fields,
-            self.get_inputs(),
-            self.catalog,
-            self.cache,
-            download_cb=self.cb,
-            processed_cb=processed_cb,
-        )
-        process_udf_outputs(
-            self.catalog.warehouse,
-            self.table,
-            self.notify_and_process(udf_results, processed_cb),
-            self.udf,
-            cb=generated_cb,
-        )
+        prefetch = self.udf.prefetch
+        with _get_cache(self.catalog.cache, prefetch, use_cache=self.cache) as _cache:
+            catalog = clone_catalog_with_cache(self.catalog, _cache)
+            udf_results = self.udf.run(
+                self.udf_fields,
+                self.get_inputs(),
+                catalog,
+                self.cache,
+                download_cb=self.cb,
+                processed_cb=processed_cb,
+            )
+            with safe_closing(udf_results):
+                process_udf_outputs(
+                    catalog.warehouse,
+                    self.table,
+                    self.notify_and_process(udf_results, processed_cb),
+                    self.udf,
+                    cb=generated_cb,
+                )
 
         put_into_queue(
             self.done_queue,

datachain/utils.py

@@ -9,6 +9,7 @@ import stat
 import sys
 import time
 from collections.abc import Iterable, Iterator, Sequence
+from contextlib import contextmanager
 from datetime import date, datetime, timezone
 from itertools import chain, islice
 from typing import TYPE_CHECKING, Any, Optional, TypeVar, Union
@@ -22,6 +23,7 @@ from pydantic import BaseModel
 
 if TYPE_CHECKING:
     import pandas as pd
+    from typing_extensions import Self
 
 NUL = b"\0"
 TIME_ZERO = datetime.fromtimestamp(0, tz=timezone.utc)
@@ -33,7 +35,7 @@ ENV_DATACHAIN_GLOBAL_CONFIG_DIR = "DATACHAIN_GLOBAL_CONFIG_DIR"
 STUDIO_URL = "https://studio.datachain.ai"
 
 
-T = TypeVar("T", bound="DataChainDir")
+T = TypeVar("T")
 
 
 class DataChainDir:
@@ -90,7 +92,7 @@ class DataChainDir:
         return osp.join(root_dir, cls.DEFAULT)
 
     @classmethod
-    def find(cls: type[T], create: bool = True) -> T:
+    def find(cls, create: bool = True) -> "Self":
         try:
             root = os.environ[cls.ENV_VAR]
         except KeyError:
@@ -479,3 +481,12 @@ def row_to_nested_dict(
     for h, v in zip(headers, row):
         nested_dict_path_set(result, h, v)
     return result
+
+
+@contextmanager
+def safe_closing(thing: T) -> Iterator[T]:
+    try:
+        yield thing
+    finally:
+        if hasattr(thing, "close"):
+            thing.close()

{datachain-0.8.4.dist-info → datachain-0.8.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: datachain
-Version: 0.8.4
+Version: 0.8.5
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -96,10 +96,10 @@ Requires-Dist: defusedxml; extra == "examples"
 Requires-Dist: accelerate; extra == "examples"
 Requires-Dist: unstructured_ingest[embed-huggingface]; extra == "examples"
 Requires-Dist: unstructured[pdf]<0.16.12; extra == "examples"
-Requires-Dist: pdfplumber==0.11.4; extra == "examples"
+Requires-Dist: pdfplumber==0.11.5; extra == "examples"
 Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
 Requires-Dist: onnx==1.16.1; extra == "examples"
-Requires-Dist: ultralytics==8.3.55; extra == "examples"
+Requires-Dist: ultralytics==8.3.58; extra == "examples"
 
 ================
 |logo| DataChain
@@ -134,7 +134,7 @@ Use Cases
 1. **ETL.** Pythonic framework for describing and running unstructured data transformations
    and enrichments, applying models to data, including LLMs.
 2. **Analytics.** DataChain dataset is a table that combines all the information about data
-   objects in one place + it provides dataframe-like API and vecrorized engine to do analytics
+   objects in one place + it provides dataframe-like API and vectorized engine to do analytics
    on these tables at scale.
 3. **Versioning.** DataChain doesn't store, require moving or copying data (unlike DVC).
    Perfect use case is a bucket with thousands or millions of images, videos, audio, PDFs.
@@ -270,7 +270,7 @@ DataChain Studio Platform
 
 `DataChain Studio`_ is a proprietary solution for teams that offers:
 
-- **Centralized dataset registry** to manage data, code and dependency
+- **Centralized dataset registry** to manage data, code and
   dependencies in one place.
 - **Data Lineage** for data sources as well as derivative dataset.
 - **UI for Multimodal Data** like images, videos, and PDFs.

{datachain-0.8.4.dist-info → datachain-0.8.5.dist-info}/RECORD

@@ -1,22 +1,22 @@
 datachain/__init__.py,sha256=ofPJ6B-d-ybSDRrE7J6wqF_ZRAB2W9U8l-eeuBtqPLg,865
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
-datachain/asyn.py,sha256=5aKrjnUxk0mtnZeFKNJd1DCE0MsnSoyJBZkr0y9H_a0,9313
-datachain/cache.py,sha256=4xI0Ct2gVXuLZPqKdbjmfb_KD2klou-9WnL1WNhIuCA,3077
+datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
+datachain/cache.py,sha256=7ABXvxhuYmXPymC_MilxxUk3iIr2y5s2FqCmh4uacaQ,3651
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
 datachain/dataset.py,sha256=5HtqZBRaaToa_C74g62bACjBaCRf2Y6BDgIACLhK1ZA,19161
 datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
-datachain/listing.py,sha256=WdiWMVa0xZ-LtR3SJ0gFLgYUI6VaLI0DSEE_KvfikXs,7582
+datachain/listing.py,sha256=1v4ryVp1EbodyA-bmfFqWHWvykfd6ww33pp9pEbozo8,7607
 datachain/node.py,sha256=HSpjBUBQBWXUUpbUEq839dsSc5KR2O8ww1Udl4jQemY,6023
 datachain/nodes_fetcher.py,sha256=ILMzUW5o4_6lUOVrLDC9gJPCXfcgKnMG68plrc7dAOA,1113
 datachain/nodes_thread_pool.py,sha256=uPo-xl8zG5m9YgODjPFBpbcqqHjI-dcxH87yAbj_qco,3192
-datachain/progress.py,sha256=jgW_MOGSyY9devjvW3Y1VkCk1z6FkQZ3qMURfRrNXMo,4342
+datachain/progress.py,sha256=V-TSrzrbmSkxegKxvXmNiGxpfBEL_XM26iVfSfbJJ-c,4962
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/studio.py,sha256=LFSX-HDRiceZDqc4pfy6q97xoejQCeWmuUGomwmOH9Y,9315
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
-datachain/utils.py,sha256=UWkPJrzGC6RiNxIvclxbchoJbuMnD0Nvf1ZO6RU6AcY,13912
+datachain/utils.py,sha256=LBeg-9n48saBTHSPk7u_j-kjJnPUAq5Oyps_peSaqlM,14128
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=ixXJKftUIG_ZBPdie1dJAPPHddWV6HZwb3GO-TRHtxY,60103
+datachain/catalog/catalog.py,sha256=tPE5aqA6rj0T19JeQdb6A8nHy76R7WwOiQMhWrUfQK8,60511
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=HA_mBC7q_My8j2WnSvIjUGuJpl6SIdg5vvy_lagxJlA,5733
 datachain/cli/__init__.py,sha256=ywf3C552rQeXAW7xemodYqxJb1pAeVQulyCJSr7xiCk,8380
@@ -34,26 +34,27 @@ datachain/cli/parser/job.py,sha256=KIs4_yIcfr09RqG5Bx7YAd-QlUs7IznUhf34OxX1z2c,3
 datachain/cli/parser/studio.py,sha256=V3LjaN8gexpMOHdshSCgfwR0LJswE4te0PLqARwwlPA,4044
 datachain/cli/parser/utils.py,sha256=exnlrEQlEa5q0Jh4w_g-1O4niyDixsDpqa1DoIQewok,1590
 datachain/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,49
-datachain/client/azure.py,sha256=D-mfLtpiq6O-DaSs-ofEEYhjIZBNfgRw1l9R7UgxEM4,3055
+datachain/client/azure.py,sha256=lK2yg24doplYsR28CAG9eNr34MJjkoYplT1Urcf0EOQ,3216
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
-datachain/client/fsspec.py,sha256=6Jwd3yaSG93NCfbRxf6I2IUi5t4nfgCp40De916IcoI,13894
-datachain/client/gcs.py,sha256=MI94GXpCRqAlaF56HNrzQbXA-yR7bn2FOBPzO-lG_SI,4947
+datachain/client/fsspec.py,sha256=ZelCVAuPnSUYuMD-l7IUsbIKNmWzTm6PKdrlK9Bw5xw,13907
+datachain/client/gcs.py,sha256=-KsOrA_SPS9xCQtizUcI3Iy9lMSY8iVxUSPINOWj7i4,5109
 datachain/client/hf.py,sha256=XeVJVbiNViZCpn3sfb90Fr8SYO3BdLmfE3hOWMoqInE,951
 datachain/client/local.py,sha256=iHQKh-HhoNzqZ2yaiuIfZWGXtt_X9FMSA-TN_03zjPc,4708
-datachain/client/s3.py,sha256=67XISS6tW9bnhlbRtKJEAYd_JQvtLHqdPBxm8ySrJl8,6440
+datachain/client/s3.py,sha256=qPwpHTD934WypEbetPgn0uAiQ31_mTitCVeQr5QkDc0,6965
 datachain/data_storage/__init__.py,sha256=9Wit-oe5P46V7CJQTD0BJ5MhOa2Y9h3ddJ4VWTe-Lec,273
-datachain/data_storage/db_engine.py,sha256=81Ol1of9TTTzD97ORajCnP366Xz2mEJt6C-kTUCaru4,3406
+datachain/data_storage/db_engine.py,sha256=n8ojCbvVMPY2e3SG8fUaaD0b9GkVfpl_Naa_6EiHfWg,3788
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
 datachain/data_storage/metastore.py,sha256=hfTITcesE9XlUTxcCcdDyWGGep-QSjJL9DUxko5QCeI,37524
-datachain/data_storage/schema.py,sha256=-QVlRvD0dfu-ZFUxylEoSnLJLnleMEjVlcAb2OGu-AY,9895
+datachain/data_storage/schema.py,sha256=8np_S6Ltq7WXfcqpoSeFPryPS7cipdbiSP6UnKJkAac,9516
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=iJv1QxwVifOowtYhIDqYVoea21dvkQIdxklGNIend3c,22961
-datachain/data_storage/warehouse.py,sha256=CMW36ZNrAzoZ003xGkdnIxC7S0PnQxC2588iUMKI9SM,30779
-datachain/func/__init__.py,sha256=mvvuIycO3emE3pgbc1GNTeYbxnvto1yloULBLBBa0g4,1055
+datachain/data_storage/sqlite.py,sha256=hz6ZBxhEID1AroY5Xs3YbgJf_o9-4JiG2OE5yN5Ci1o,23176
+datachain/data_storage/warehouse.py,sha256=gFAzkt_lNF0KoKylwtmQ9sLg4Soc6AVho0nvkUX67_0,30823
+datachain/diff/__init__.py,sha256=OapNRBsyGDOQHelefUEoXoFHRWCJuBnhvD0ibebKvBc,10486
+datachain/func/__init__.py,sha256=8WWvzWYtOzXmAC1fOMegyoJ-rFnpAca_5UW4gy8BVsk,1077
 datachain/func/aggregate.py,sha256=7_IPrIwb2XSs3zG4iOr1eTvzn6kNVe2mkzvNzjusDHk,10942
 datachain/func/array.py,sha256=zHDNWuWLA7HVa9FEvQeHhVi00_xqenyleTqcLwkXWBI,5477
 datachain/func/base.py,sha256=wA0sBQAVyN9LPxoo7Ox83peS0zUVnyuKxukwAcjGLfY,534
-datachain/func/conditional.py,sha256=iMh13mmeVJq8xa856suPD4ozDWo6-fs3nRtNhmLXGhg,3998
+datachain/func/conditional.py,sha256=AfvGQKBFOJ-wkmDTH0P7pmq42Zf1DRcYRsLGurdAiJE,4766
 datachain/func/func.py,sha256=4FJYMqeGD6xNe5ahrFgfthi0DTFb5w3QDLlXxbpHZjU,15371
 datachain/func/numeric.py,sha256=gMe1Ks0dqQKHkjcpvj7I5S-neECzQ_gltPQLNoaWOyo,5632
 datachain/func/path.py,sha256=mqN_mfkwv44z2II7DMTp_fGGw95hmTCNls_TOFNpr4k,3155
@@ -61,25 +62,24 @@ datachain/func/random.py,sha256=pENOLj9rSmWfGCnOsUIaCsVC5486zQb66qfQvXaz9Z4,452
 datachain/func/string.py,sha256=8az3BTeezlaZt6NW-54GWX7WSosAOVMbTr6bXIYyJq4,5958
 datachain/func/window.py,sha256=0MB1yjpVbwOrl_WNLZ8V3jkJz3o0XlYinpAcZQJuxiA,1688
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/lib/arrow.py,sha256=pclruEeTffWZToeDlYDkWdlHZIyXb1YYFSjyutf8CDk,9867
+datachain/lib/arrow.py,sha256=N1s59qNLtkpGRk400pztuukzekC_Yt_hvNfhul7Rf_Y,9902
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=zS4lmXHVBXc9ntcyea2a1CRLXGSAN_0glXcF88CohgY,2685
 datachain/lib/dataset_info.py,sha256=IjdF1E0TQNOq9YyynfWiCFTeZpbyGfyJvxgJY4YN810,2493
-datachain/lib/dc.py,sha256=5AolChfT41QLhzVX1zaNRsZfQ8BAhLDZVvgu8qiU3jg,91145
-datachain/lib/diff.py,sha256=Yurzyi7PzZzY80HOnVTpwtbWzSJ1LqN8NgZWwZOh_UU,6732
-datachain/lib/file.py,sha256=JQ8GfqBwIikdaeSaQzbHo04DZWwNNk_Cgsofh1X7eg8,15047
-datachain/lib/hf.py,sha256=a-zFpDmZIR4r8dlNNTjfpAKSnuJ9xyRXlgcdENiXt3E,5864
+datachain/lib/dc.py,sha256=qwZzHQ0blx3nddmNIHjRYaGcsDfoAVIhWYEYeRq8p4Q,91234
+datachain/lib/file.py,sha256=VGC5Bj5BGLIj-6KOICP_H7IbRhYsKuGoh293GCmJCfs,15440
+datachain/lib/hf.py,sha256=CfRbT3VQ8_siLQ0tFuvNwx4n4D2m4AfEjJ9MKO7Ukww,5877
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
 datachain/lib/listing.py,sha256=6TRVCoXzC83wLFSyVOdA90_yxbKUmgcVYgIDSYuixiA,6621
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=hDPfEkcmiLZOjhBBXuareMdnq65Wj8vZvxjmum6cROM,6377
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
-datachain/lib/pytorch.py,sha256=dA3r1JY0wqV_907a1D0lFaEN-7v3fMRpc1ePFE9CnvA,6168
+datachain/lib/pytorch.py,sha256=hExKapbOSA9Bw1DQZd4tMf_xnZ9nCwygSGU9EGUW9Jo,7641
 datachain/lib/settings.py,sha256=ZELRCTLbi5vzRPiDX6cQ9LLg9TefJ_A05gIGni0lll8,2535
 datachain/lib/signal_schema.py,sha256=ps5od6zhWtdX3Khx2fwArl2xlGkK8SKi6vCQ6QmbaR0,27404
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=Rsf_6mN6qCQVknl99yvi1guta1AMnG9MsoPn14ff5Fc,13609
+datachain/lib/udf.py,sha256=gTdUTa2qKpmVQqkYMotXGUvFjiTCUrqR14FctazDcfc,14995
 datachain/lib/udf_signature.py,sha256=GXw24A-Olna6DWCdgy2bC-gZh_gLGPQ-KvjuI6pUjC0,7281
 datachain/lib/utils.py,sha256=QrjVs_oLRXEotOPUYurBJypBFi_ReTJmxcnJeH4j2Uk,1596
 datachain/lib/vfile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -101,8 +101,8 @@ datachain/model/ultralytics/pose.py,sha256=71KBTcoST2wcEtsyGXqLVpvUtqbp9gwZGA15p
 datachain/model/ultralytics/segment.py,sha256=Z1ab0tZRJubSYNH4KkFlzhYeGNTfAyC71KmkQcToHDQ,2760
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=6w8gzLTmLeylststu-gT5jIqEfi4-djS7_yTYyeo-fw,4190
-datachain/query/dataset.py,sha256=1wJuiFgXgtYarJAgLmgQESrvp0ayIQbJUiCZyAe0NkU,54774
-datachain/query/dispatch.py,sha256=Uw4highKfs70ioEddSK2zknjpvz_q59OHc8s43nXa_I,12004
+datachain/query/dataset.py,sha256=VL9iyVlX3jvir5XVnVxvfM2msBvxFsJGiwXaKkJIrmY,56148
+datachain/query/dispatch.py,sha256=_1vjeQ1wjUoxlik55k0JkWqQCUfMjgVWmEOyWRkx0dU,12437
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
 datachain/query/queue.py,sha256=waqM_KzavU8C-G95-4211Nd4GXna_u2747Chgwtgz2w,3839
@@ -133,9 +133,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=z3zRJNzjWrpPuRw-zgFbCOBKInyYxJew8ygrYQRQLNc,2930
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.8.4.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.8.4.dist-info/METADATA,sha256=s91ugEL68b3G1-Fv85lcMTj3C2LiKhlzSLrPP5hrb0E,11075
-datachain-0.8.4.dist-info/WHEEL,sha256=A3WOREP4zgxI0fKrHUG8DC8013e3dK3n7a6HDbcEIwE,91
-datachain-0.8.4.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.8.4.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.8.4.dist-info/RECORD,,
+datachain-0.8.5.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.8.5.dist-info/METADATA,sha256=hwFSeah_bNcAtJvdN_xPnvAFjz17hoK2MCHQbtUZD9I,11064
+datachain-0.8.5.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+datachain-0.8.5.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.8.5.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.8.5.dist-info/RECORD,,

{datachain-0.8.4.dist-info → datachain-0.8.5.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.7.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any