datachain 0.5.1__py3-none-any.whl → 0.6.1__py3-none-any.whl

datachain/query/schema.py

@@ -1,16 +1,13 @@
 import functools
-import json
 from abc import ABC, abstractmethod
-from datetime import datetime, timezone
 from fnmatch import fnmatch
-from typing import TYPE_CHECKING, Any, Callable, ClassVar, Optional, Union
+from typing import TYPE_CHECKING, Any, Callable, Optional, Union
 
 import attrs
 import sqlalchemy as sa
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
 
 from datachain.lib.file import File
-from datachain.sql.types import JSON, Boolean, DateTime, Int64, SQLType, String
 
 if TYPE_CHECKING:
     from datachain.catalog import Catalog
@@ -228,61 +225,4 @@ def normalize_param(param: UDFParamSpec) -> UDFParameter:
     raise TypeError(f"Invalid UDF parameter: {param}")
 
 
-class DatasetRow:
-    schema: ClassVar[dict[str, type[SQLType]]] = {
-        "source": String,
-        "path": String,
-        "size": Int64,
-        "location": JSON,
-        "is_latest": Boolean,
-        "last_modified": DateTime,
-        "version": String,
-        "etag": String,
-    }
-
-    @staticmethod
-    def create(
-        path: str,
-        source: str = "",
-        size: int = 0,
-        location: Optional[dict[str, Any]] = None,
-        is_latest: bool = True,
-        last_modified: Optional[datetime] = None,
-        version: str = "",
-        etag: str = "",
-    ) -> tuple[
-        str,
-        str,
-        int,
-        Optional[str],
-        int,
-        bool,
-        datetime,
-        str,
-        str,
-        int,
-    ]:
-        if location:
-            location = json.dumps([location])  # type: ignore [assignment]
-
-        last_modified = last_modified or datetime.now(timezone.utc)
-
-        return (  # type: ignore [return-value]
-            source,
-            path,
-            size,
-            location,
-            is_latest,
-            last_modified,
-            version,
-            etag,
-        )
-
-    @staticmethod
-    def extend(**columns):
-        cols = {**DatasetRow.schema}
-        cols.update(columns)
-        return cols
-
-
 C = Column

datachain/query/session.py

@@ -1,9 +1,9 @@
 import atexit
+import gc
 import logging
-import os
 import re
 import sys
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING, ClassVar, Optional
 from uuid import uuid4
 
 from datachain.catalog import get_catalog
@@ -11,6 +11,7 @@ from datachain.error import TableMissingError
 
 if TYPE_CHECKING:
     from datachain.catalog import Catalog
+    from datachain.dataset import DatasetRecord
 
 logger = logging.getLogger("datachain")
 
@@ -39,7 +40,7 @@ class Session:
     """
 
     GLOBAL_SESSION_CTX: Optional["Session"] = None
-    GLOBAL_SESSION: Optional["Session"] = None
+    SESSION_CONTEXTS: ClassVar[list["Session"]] = []
     ORIGINAL_EXCEPT_HOOK = None
 
     DATASET_PREFIX = "session_"
@@ -64,18 +65,21 @@ class Session:
 
         session_uuid = uuid4().hex[: self.SESSION_UUID_LEN]
         self.name = f"{name}_{session_uuid}"
-        self.job_id = os.getenv("DATACHAIN_JOB_ID") or str(uuid4())
         self.is_new_catalog = not catalog
         self.catalog = catalog or get_catalog(
             client_config=client_config, in_memory=in_memory
         )
+        self.dataset_versions: list[tuple[DatasetRecord, int]] = []
 
     def __enter__(self):
+        # Push the current context onto the stack
+        Session.SESSION_CONTEXTS.append(self)
+
         return self
 
     def __exit__(self, exc_type, exc_val, exc_tb):
         if exc_type:
-            self._cleanup_created_versions(self.name)
+            self._cleanup_created_versions()
 
         self._cleanup_temp_datasets()
         if self.is_new_catalog:
@@ -83,6 +87,12 @@ class Session:
             self.catalog.warehouse.close_on_exit()
             self.catalog.id_generator.close_on_exit()
 
+        if Session.SESSION_CONTEXTS:
+            Session.SESSION_CONTEXTS.pop()
+
+    def add_dataset_version(self, dataset: "DatasetRecord", version: int) -> None:
+        self.dataset_versions.append((dataset, version))
+
     def generate_temp_dataset_name(self) -> str:
         return self.get_temp_prefix() + uuid4().hex[: self.TEMP_TABLE_UUID_LEN]
 
@@ -98,21 +108,15 @@ class Session:
         except TableMissingError:
             pass
 
-    def _cleanup_created_versions(self, job_id: str) -> None:
-        versions = self.catalog.metastore.get_job_dataset_versions(job_id)
-        if not versions:
+    def _cleanup_created_versions(self) -> None:
+        if not self.dataset_versions:
             return
 
-        datasets = {}
-        for dataset_name, version in versions:
-            if dataset_name not in datasets:
-                datasets[dataset_name] = self.catalog.get_dataset(dataset_name)
-            dataset = datasets[dataset_name]
-            logger.info(
-                "Removing dataset version %s@%s due to exception", dataset_name, version
-            )
+        for dataset, version in self.dataset_versions:
             self.catalog.remove_dataset_version(dataset, version)
 
+        self.dataset_versions.clear()
+
     @classmethod
     def get(
         cls,
@@ -125,33 +129,34 @@ class Session:
 
         Parameters:
             session (Session): Optional Session(). If not provided a new session will
-                    be created. It's needed mostly for simplie API purposes.
-            catalog (Catalog): Optional catalog. By default a new catalog is created.
+                    be created. It's needed mostly for simple API purposes.
+            catalog (Catalog): Optional catalog. By default, a new catalog is created.
         """
         if session:
             return session
 
-        if cls.GLOBAL_SESSION is None:
+        # Access the active (most recent) context from the stack
+        if cls.SESSION_CONTEXTS:
+            return cls.SESSION_CONTEXTS[-1]
+
+        if cls.GLOBAL_SESSION_CTX is None:
             cls.GLOBAL_SESSION_CTX = Session(
                 cls.GLOBAL_SESSION_NAME,
                 catalog,
                 client_config=client_config,
                 in_memory=in_memory,
             )
-            cls.GLOBAL_SESSION = cls.GLOBAL_SESSION_CTX.__enter__()
 
             atexit.register(cls._global_cleanup)
             cls.ORIGINAL_EXCEPT_HOOK = sys.excepthook
             sys.excepthook = cls.except_hook
 
-        return cls.GLOBAL_SESSION
+        return cls.GLOBAL_SESSION_CTX
 
     @staticmethod
     def except_hook(exc_type, exc_value, exc_traceback):
+        Session.GLOBAL_SESSION_CTX.__exit__(exc_type, exc_value, exc_traceback)
         Session._global_cleanup()
-        if Session.GLOBAL_SESSION_CTX is not None:
-            job_id = Session.GLOBAL_SESSION_CTX.job_id
-            Session.GLOBAL_SESSION_CTX._cleanup_created_versions(job_id)
 
         if Session.ORIGINAL_EXCEPT_HOOK:
             Session.ORIGINAL_EXCEPT_HOOK(exc_type, exc_value, exc_traceback)
@@ -160,7 +165,6 @@ class Session:
     def cleanup_for_tests(cls):
         if cls.GLOBAL_SESSION_CTX is not None:
             cls.GLOBAL_SESSION_CTX.__exit__(None, None, None)
-            cls.GLOBAL_SESSION = None
             cls.GLOBAL_SESSION_CTX = None
             atexit.unregister(cls._global_cleanup)
 
@@ -171,3 +175,7 @@ class Session:
     def _global_cleanup():
         if Session.GLOBAL_SESSION_CTX is not None:
             Session.GLOBAL_SESSION_CTX.__exit__(None, None, None)
+
+        for obj in gc.get_objects():  # Get all tracked objects
+            if isinstance(obj, Session):  # Cleanup temp dataset for session variables.
+                obj.__exit__(None, None, None)

datachain/sql/functions/__init__.py

@@ -1,7 +1,7 @@
 from sqlalchemy.sql.expression import func
 
 from . import array, path, string
-from .array import avg
+from .aggregate import avg
 from .conditional import greatest, least
 from .random import rand
 

datachain/sql/functions/aggregate.py

@@ -0,0 +1,47 @@
+from sqlalchemy.sql.functions import GenericFunction, ReturnTypeFromArgs
+
+from datachain.sql.types import Float, String
+from datachain.sql.utils import compiler_not_implemented
+
+
+class avg(GenericFunction):  # noqa: N801
+    """
+    Returns the average of the column.
+    """
+
+    type = Float()
+    package = "array"
+    name = "avg"
+    inherit_cache = True
+
+
+class group_concat(GenericFunction):  # noqa: N801
+    """
+    Returns the concatenated string of the column.
+    """
+
+    type = String()
+    package = "array"
+    name = "group_concat"
+    inherit_cache = True
+
+
+class any_value(ReturnTypeFromArgs):  # noqa: N801
+    """
+    Returns first value of the column.
+    """
+
+    inherit_cache = True
+
+
+class collect(ReturnTypeFromArgs):  # noqa: N801
+    """
+    Returns an array of the column.
+    """
+
+    inherit_cache = True
+
+
+compiler_not_implemented(avg)
+compiler_not_implemented(group_concat)
+compiler_not_implemented(any_value)

datachain/sql/functions/array.py

@@ -44,15 +44,7 @@ class sip_hash_64(GenericFunction):  # noqa: N801
     inherit_cache = True
 
 
-class avg(GenericFunction):  # noqa: N801
-    type = Float()
-    package = "array"
-    name = "avg"
-    inherit_cache = True
-
-
 compiler_not_implemented(cosine_distance)
 compiler_not_implemented(euclidean_distance)
 compiler_not_implemented(length)
 compiler_not_implemented(sip_hash_64)
-compiler_not_implemented(avg)

datachain/sql/functions/string.py

@@ -37,6 +37,18 @@ class regexp_replace(GenericFunction):  # noqa: N801
     inherit_cache = True
 
 
+class replace(GenericFunction):  # noqa: N801
+    """
+    Replaces substring with another string.
+    """
+
+    type = String()
+    package = "string"
+    name = "replace"
+    inherit_cache = True
+
+
 compiler_not_implemented(length)
 compiler_not_implemented(split)
 compiler_not_implemented(regexp_replace)
+compiler_not_implemented(replace)

datachain/sql/sqlite/base.py

@@ -14,7 +14,7 @@ from sqlalchemy.sql.elements import literal
 from sqlalchemy.sql.expression import case
 from sqlalchemy.sql.functions import func
 
-from datachain.sql.functions import array, conditional, random, string
+from datachain.sql.functions import aggregate, array, conditional, random, string
 from datachain.sql.functions import path as sql_path
 from datachain.sql.selectable import Values, base_values_compiler
 from datachain.sql.sqlite.types import (
@@ -78,12 +78,16 @@ def setup():
     compiles(array.length, "sqlite")(compile_array_length)
     compiles(string.length, "sqlite")(compile_string_length)
     compiles(string.split, "sqlite")(compile_string_split)
-    compiles(string.regexp_replace, "sqlite")(compile_regexp_replace)
+    compiles(string.regexp_replace, "sqlite")(compile_string_regexp_replace)
+    compiles(string.replace, "sqlite")(compile_string_replace)
     compiles(conditional.greatest, "sqlite")(compile_greatest)
     compiles(conditional.least, "sqlite")(compile_least)
     compiles(Values, "sqlite")(compile_values)
     compiles(random.rand, "sqlite")(compile_rand)
-    compiles(array.avg, "sqlite")(compile_avg)
+    compiles(aggregate.avg, "sqlite")(compile_avg)
+    compiles(aggregate.group_concat, "sqlite")(compile_group_concat)
+    compiles(aggregate.any_value, "sqlite")(compile_any_value)
+    compiles(aggregate.collect, "sqlite")(compile_collect)
 
     if load_usearch_extension(sqlite3.connect(":memory:")):
         compiles(array.cosine_distance, "sqlite")(compile_cosine_distance_ext)
@@ -273,10 +277,6 @@ def path_file_ext(path):
     return func.substr(path, func.length(path) - path_file_ext_length(path) + 1)
 
 
-def compile_regexp_replace(element, compiler, **kwargs):
-    return f"regexp_replace({compiler.process(element.clauses, **kwargs)})"
-
-
 def compile_path_parent(element, compiler, **kwargs):
     return compiler.process(path_parent(*element.clauses.clauses), **kwargs)
 
@@ -331,6 +331,14 @@ def compile_string_split(element, compiler, **kwargs):
     return compiler.process(func.split(*element.clauses.clauses), **kwargs)
 
 
+def compile_string_regexp_replace(element, compiler, **kwargs):
+    return f"regexp_replace({compiler.process(element.clauses, **kwargs)})"
+
+
+def compile_string_replace(element, compiler, **kwargs):
+    return compiler.process(func.replace(*element.clauses.clauses), **kwargs)
+
+
 def compile_greatest(element, compiler, **kwargs):
     """
     Compiles a sql function for `greatest(*args)` taking 1 or more args
@@ -395,6 +403,21 @@ def compile_avg(element, compiler, **kwargs):
     return compiler.process(func.avg(*element.clauses.clauses), **kwargs)
 
 
+def compile_group_concat(element, compiler, **kwargs):
+    return compiler.process(func.aggregate_strings(*element.clauses.clauses), **kwargs)
+
+
+def compile_any_value(element, compiler, **kwargs):
+    # use bare column to return any value from the group,
+    # this is documented behavior for sqlite,
+    # see https://www.sqlite.org/lang_select.html#bare_columns_in_an_aggregate_query
+    return compiler.process(*element.clauses.clauses, **kwargs)
+
+
+def compile_collect(element, compiler, **kwargs):
+    return compiler.process(func.json_group_array(*element.clauses.clauses), **kwargs)
+
+
 def load_usearch_extension(conn) -> bool:
     try:
         # usearch is part of the vector optional dependencies

{datachain-0.5.1.dist-info → datachain-0.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.5.1
+Version: 0.6.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -46,7 +46,7 @@ Requires-Dist: iterative-telemetry >=0.0.9
 Requires-Dist: numpy <2,>=1 ; sys_platform == "win32"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests] ; extra == 'dev'
-Requires-Dist: mypy ==1.11.2 ; extra == 'dev'
+Requires-Dist: mypy ==1.12.0 ; extra == 'dev'
 Requires-Dist: types-python-dateutil ; extra == 'dev'
 Requires-Dist: types-pytz ; extra == 'dev'
 Requires-Dist: types-PyYAML ; extra == 'dev'

{datachain-0.5.1.dist-info → datachain-0.6.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=ofPJ6B-d-ybSDRrE7J6wqF_ZRAB2W9U8l-eeuBtqPLg,865
+datachain/__init__.py,sha256=OGzc8xZWtwqxiiutjU4AxCRPY0lrX_csgERiTrq4G0o,908
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=Lg3Ck1PQLjQziMx9KU4atzbEnJXTE0924WMYkhgWtGU,8247
 datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
@@ -18,7 +18,7 @@ datachain/storage.py,sha256=RiSJLYdHUjnrEWkLBKPcETHpAxld_B2WxLg711t0aZI,3733
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=KeFSRHsiYthnTu4a6bH-rw04mX1m8krTX0f2NqfQGFI,12114
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=BsMyk2RQibQYHgrmovFZeSEpPVMTwgb_7ntVYdc7t-E,64090
+datachain/catalog/catalog.py,sha256=r5lkwwZDh8cETNniBdzPCY9Ix8G-1RdkehjvUe3d2nE,63834
 datachain/catalog/datasource.py,sha256=D-VWIVDCM10A8sQavLhRXdYSCG7F4o4ifswEF80_NAQ,1412
 datachain/catalog/loader.py,sha256=-6VelNfXUdgUnwInVyA8g86Boxv2xqhTh9xNS-Zlwig,8242
 datachain/client/__init__.py,sha256=T4wiYL9KIM0ZZ_UqIyzV8_ufzYlewmizlV4iymHNluE,86
@@ -36,14 +36,14 @@ datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s
 datachain/data_storage/metastore.py,sha256=HfCxk4lmDUg2Q4WsFNQGMWxllP0mToA00fxkFTwdNIE,52919
 datachain/data_storage/schema.py,sha256=AGbjyEir5UmRZXI3m0jChZogUh5wd8csj6-YlUWaAxQ,8383
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=fW08P7AbJ0cDbTbcTKuAGpvMXvBjg-QkGsKT_Dslyws,28383
-datachain/data_storage/warehouse.py,sha256=fXhVfao3NfWFGbbG5uJ-Ga4bX1FiKVfcbDyQgECYfk8,32122
+datachain/data_storage/sqlite.py,sha256=V8fGRPjSwIT7kdw1qyQfUfdqGjXB8dE68npkyXfKW0o,28702
+datachain/data_storage/warehouse.py,sha256=Ea0wVcWxe7Bu-8V8eqrPJ8Ov5-DT1dvv1MgxMINettc,31931
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/arrow.py,sha256=0R2CYsN82nNa5_03iS6jVix9EKeeqNZNAMgpSQP2hfo,9482
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
-datachain/lib/data_model.py,sha256=gHIjlow84GMRDa78yLL1Ud-N18or21fnTyPEwsatpXY,2045
+datachain/lib/data_model.py,sha256=ECTbvlnzM98hp2mZ4fo82Yi0-MuoqTIQasQKGIyd89I,2040
 datachain/lib/dataset_info.py,sha256=srPPhI2UHf6hFPBecyFEVw2SS5aPisIIMsvGgKqi7ss,2366
-datachain/lib/dc.py,sha256=HLOAkJEKFHJV_PqwSu0Pyl1m7JmUea8_wiMJFr14Nfk,75960
+datachain/lib/dc.py,sha256=wEqBDCENfBmeow0-uu8R4qJhQa8taEIzveUiNdr2CyY,78341
 datachain/lib/file.py,sha256=LjTW_-PDAnoUhvyB4bJ8Y8n__XGqrxvmd9mDOF0Gir8,14875
 datachain/lib/hf.py,sha256=cPnmLuprr0pYABH7KqA5FARQ1JGlywdDwD3yDzVAm4k,5920
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
@@ -53,30 +53,33 @@ datachain/lib/meta_formats.py,sha256=3f-0vpMTesagS9iMd3y9-u9r-7g0eqYsxmK4fVfNWlw
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
 datachain/lib/pytorch.py,sha256=W-ARi2xH1f1DUkVfRuerW-YWYgSaJASmNCxtz2lrJGI,6072
 datachain/lib/settings.py,sha256=39thOpYJw-zPirzeNO6pmRC2vPrQvt4eBsw1xLWDFsw,2344
-datachain/lib/signal_schema.py,sha256=iqgubjCBRiUJB30miv05qFX4uU04dA_Pzi3DCUsHZGs,24177
+datachain/lib/signal_schema.py,sha256=6fgQIZz4jFvuiaL1mqK5Cq6yr4WC57o2ptHxk36MRNY,24438
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=oHhJWb0gVTxcybGzYDzAeN0Gb1IMhZBoGefncT88dIY,12339
+datachain/lib/udf.py,sha256=GvhWLCXZUY7sz1QMRBj1AJDSzzhyj15xs3Ia9hjJrJE,12697
 datachain/lib/udf_signature.py,sha256=GXw24A-Olna6DWCdgy2bC-gZh_gLGPQ-KvjuI6pUjC0,7281
-datachain/lib/utils.py,sha256=5-kJlAZE0D9nXXweAjo7-SP_AWGo28feaDByONYaooQ,463
+datachain/lib/utils.py,sha256=12elAX6eTFgMGKIf2UfZ4IW07kRwjK6wz8yGE41RtNM,618
 datachain/lib/vfile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/webdataset.py,sha256=o7SHk5HOUWsZ5Ln04xOM04eQqiBHiJNO7xLgyVBrwo8,6924
 datachain/lib/webdataset_laion.py,sha256=aGMWeFmeYNK75ewO9JTA11iB1i3QtTzUfenQA5jajfo,2535
 datachain/lib/convert/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/convert/flatten.py,sha256=Uebc5CeqCsacp-nr6IG9i6OGuUavXqdqnoGctZBk3RQ,1384
 datachain/lib/convert/python_to_sql.py,sha256=40SAOdoOgikZRhn8iomCPDRoxC3RFxjJLivEAA9MHDU,2880
-datachain/lib/convert/sql_to_python.py,sha256=lGnKzSF_tz9Y_5SSKkrIU95QEjpcDzvOxIRkEKTQag0,443
+datachain/lib/convert/sql_to_python.py,sha256=XXCBYDQFUXJIBNWkjEP944cnCfJ8GF2Tji0DLF3A_zQ,315
 datachain/lib/convert/unflatten.py,sha256=Ogvh_5wg2f38_At_1lN0D_e2uZOOpYEvwvB2xdq56Tw,2012
-datachain/lib/convert/values_to_tuples.py,sha256=YOdbjzHq-uj6-cV2Qq43G72eN2avMNDGl4x5t6yQMl8,3931
-datachain/query/__init__.py,sha256=0NBOZVgIDpCcj1Ci883dQ9A0iiwe03xzmotkOCFbxYc,293
-datachain/query/batch.py,sha256=-vlpINJiertlnaoUVv1C95RatU0F6zuhpIYRufJRo1M,3660
-datachain/query/dataset.py,sha256=1c7y178ccFSeL_WIba0vT87Md_Oo4F8zaTVDjB9Bp3I,53641
-datachain/query/dispatch.py,sha256=JVcZ4REE_GOsqXbar_Cb_fk-pHgQoabQLzXwuu7IhOg,12409
+datachain/lib/convert/values_to_tuples.py,sha256=varRCnSMT_pZmHznrd2Yi05qXLLz_v9YH_pOCpHSkdc,3921
+datachain/lib/func/__init__.py,sha256=ucJ15J_Q5Hy--boKV-tPuhKagVD3NpnuUPhLtDp7doI,230
+datachain/lib/func/aggregate.py,sha256=B5VV6WoSYYiO_9uN4_nXPMkF9OOkgyE6suJ7XD-JiPI,938
+datachain/lib/func/func.py,sha256=kFhVZlWZzgAfM7-DpkpZWf5zzdEutp_3NxIFWxXww_I,1956
+datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
+datachain/query/batch.py,sha256=5fEhORFe7li12SdYddaSK3LyqksMfCHhwN1_A6TfsA4,3485
+datachain/query/dataset.py,sha256=-J8t8XGUQveh-4aM5HrnbYx9xLfMQ8p6P9sKmBaTpLU,52683
+datachain/query/dispatch.py,sha256=wjjTWw6sFQbB9SKRh78VbfvwSMgJXCfqJklS3-9KnCU,12025
 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
-datachain/query/schema.py,sha256=I8zLWJuWl5N332ni9mAzDYtcxMJupVPgWkSDe8spNEk,8019
-datachain/query/session.py,sha256=kpFFJMfWBnxaMPojMGhJRbk-BOsSYI8Ckl6vvqnx7d0,5787
+datachain/query/schema.py,sha256=b_KnVy6B26Ol4nYG0LqNNpeQ1QYPk95YRGUjXfdaQWs,6606
+datachain/query/session.py,sha256=50SOdLNCjqHHKI-L4xGXyzTVxzMWfANqKqjeYre-c2k,5959
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/remote/studio.py,sha256=f5s6qSZ9uB4URGUoU_8_W1KZRRQQVSm6cgEBkBUEfuE,7226
 datachain/sql/__init__.py,sha256=A2djrbQwSMUZZEIKGnm-mnRA-NDSbiDJNpAmmwGNyIo,303
@@ -85,20 +88,21 @@ datachain/sql/types.py,sha256=3aXpoxkmCYbw0Dlta5J1enwS8_FuvjfSqyrNZO-dWj4,13383
 datachain/sql/utils.py,sha256=rzlJw08etivdrcuQPqNVvVWhuVSyUPUQEEc6DOhu258,818
 datachain/sql/default/__init__.py,sha256=XQ2cEZpzWiABqjV-6yYHUBGI9vN_UHxbxZENESmVAWw,45
 datachain/sql/default/base.py,sha256=QD-31C6JnyOXzogyDx90sUhm7QvgXIYpeHEASH84igU,628
-datachain/sql/functions/__init__.py,sha256=Ioyy7nSetrTLVnHGcGcmZU99HxUFcx-5PFbrh2dPNH0,396
-datachain/sql/functions/array.py,sha256=EB7nJSncUc1PuxlHyzU2gVhF8DuXaxpGlxb5e8X2KFY,1297
+datachain/sql/functions/__init__.py,sha256=-vIkU0AqwOW5FX6P89xYl-uBIUdt46CEnCtshmN85gM,400
+datachain/sql/functions/aggregate.py,sha256=3AQdA8YHPFdtCEfwZKQXTT8SlQWdG9gD5PBtGN3Odqs,944
+datachain/sql/functions/array.py,sha256=rvH27SWN9gdh_mFnp0GIiXuCrNW6n8ZbY4I_JUS-_e0,1140
 datachain/sql/functions/conditional.py,sha256=q7YUKfunXeEldXaxgT-p5pUTcOEVU_tcQ2BJlquTRPs,207
 datachain/sql/functions/path.py,sha256=zixpERotTFP6LZ7I4TiGtyRA8kXOoZmH1yzH9oRW0mg,1294
 datachain/sql/functions/random.py,sha256=vBwEEj98VH4LjWixUCygQ5Bz1mv1nohsCG0-ZTELlVg,271
-datachain/sql/functions/string.py,sha256=NSQIpmtQgm68hz3TFJsgHMBuo4MjBNhDSyEIC3pWkT8,916
+datachain/sql/functions/string.py,sha256=DYgiw8XSk7ge7GXvyRI1zbaMruIizNeI-puOjriQGZQ,1148
 datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7d04,166
-datachain/sql/sqlite/base.py,sha256=WLPHBhZbXbiqPoRV1VgDrXJqku4UuvJpBhYeQ0k5rI8,13364
+datachain/sql/sqlite/base.py,sha256=aHSZVvh4XSVkvZ07h3jMoRlHI4sWD8y3SnmGs9xMG9Y,14375
 datachain/sql/sqlite/types.py,sha256=yzvp0sXSEoEYXs6zaYC_2YubarQoZH-MiUNXcpuEP4s,1573
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.5.1.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.5.1.dist-info/METADATA,sha256=n8TFKjDmTzNBMaW5Oa6MUUUOAQbAjPzkAMaKCW3Y9NU,17156
-datachain-0.5.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-datachain-0.5.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.5.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.5.1.dist-info/RECORD,,
+datachain-0.6.1.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.6.1.dist-info/METADATA,sha256=kOEDXkaNjPHB-A1fLt60s_EJvnjuLIU3xdfp5UhflUA,17156
+datachain-0.6.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+datachain-0.6.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.6.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.6.1.dist-info/RECORD,,