datachain 0.2.0__py3-none-any.whl → 0.2.1__py3-none-any.whl

datachain/__init__.py

@@ -1,4 +0,0 @@
-try:
-    from ._version import version as __version__
-except ImportError:
-    __version__ = "UNKNOWN"

datachain/cli.py

@@ -5,13 +5,14 @@ import sys
 import traceback
 from argparse import SUPPRESS, Action, ArgumentParser, ArgumentTypeError, Namespace
 from collections.abc import Iterable, Iterator, Mapping, Sequence
+from importlib.metadata import PackageNotFoundError, version
 from itertools import chain
 from multiprocessing import freeze_support
 from typing import TYPE_CHECKING, Optional, Union
 
 import shtab
 
-from datachain import __version__, utils
+from datachain import utils
 from datachain.cli_utils import BooleanOptionalAction, CommaSeparatedArgs, KeyValueArgs
 from datachain.utils import DataChainDir
 
@@ -96,6 +97,12 @@ def add_show_args(parser: ArgumentParser) -> None:
 
 
 def get_parser() -> ArgumentParser:  # noqa: PLR0915
+    try:
+        __version__ = version("datachain")
+    except PackageNotFoundError:
+        # package is not installed
+        __version__ = "unknown"
+
     parser = ArgumentParser(
         description="DataChain: Wrangle unstructured AI data at scale", prog="datachain"
     )

datachain/data_storage/schema.py

@@ -31,7 +31,7 @@ def dedup_columns(columns: Iterable[sa.Column]) -> list[sa.Column]:
     """
     c_set: dict[str, sa.Column] = {}
     for c in columns:
-        if ec := c_set.get(c.name, None):
+        if (ec := c_set.get(c.name, None)) is not None:
             if str(ec.type) != str(c.type):
                 raise ValueError(
                     f"conflicting types for column {c.name}:{c.type!s} and {ec.type!s}"
@@ -171,8 +171,8 @@ class DataTable:
     ):
         # copy columns, since re-using the same objects from another table
         # may raise an error
-        columns = [cls.copy_column(c) for c in columns if c.name != "id"]
-        columns = [sa.Column("id", Int, primary_key=True), *columns]
+        columns = cls.sys_columns() + [cls.copy_column(c) for c in columns]
+        columns = dedup_columns(columns)
 
         if metadata is None:
             metadata = sa.MetaData()
@@ -230,11 +230,17 @@ class DataTable:
     def delete(self):
         return self.apply_conditions(self.table.delete())
 
+    @staticmethod
+    def sys_columns():
+        return [
+            sa.Column("id", Int, primary_key=True),
+            sa.Column("random", Int64, nullable=False, default=f.random()),
+        ]
+
     @classmethod
     def file_columns(cls) -> list[sa.Column]:
         return [
-            sa.Column("id", Int, primary_key=True),
-            sa.Column("random", Int64, nullable=False),
+            *cls.sys_columns(),
             sa.Column("vtype", String, nullable=False, index=True),
             sa.Column("dir_type", Int, index=True),
             sa.Column("parent", String, index=True),

datachain/data_storage/sqlite.py

@@ -33,6 +33,7 @@ from datachain.data_storage.schema import (
 from datachain.dataset import DatasetRecord
 from datachain.error import DataChainError
 from datachain.sql.sqlite import create_user_defined_sql_functions, sqlite_dialect
+from datachain.sql.sqlite.base import load_usearch_extension
 from datachain.sql.types import SQLType
 from datachain.storage import StorageURI
 from datachain.utils import DataChainDir
@@ -114,6 +115,8 @@ class SQLiteDatabaseEngine(DatabaseEngine):
             if os.environ.get("DEBUG_SHOW_SQL_QUERIES"):
                 db.set_trace_callback(print)
 
+            load_usearch_extension(db)
+
             return cls(engine, MetaData(), db, db_file)
         except RuntimeError:
             raise DataChainError("Can't connect to SQLite DB") from None

datachain/lib/cached_stream.py

@@ -1,6 +1,3 @@
-import os
-import shutil
-import tempfile
 from abc import ABC
 from contextlib import AbstractContextManager
 
@@ -8,9 +5,7 @@ from datachain.cache import UniqueId
 
 
 class AbstractCachedStream(AbstractContextManager, ABC):
-    def __init__(self, stream, size, catalog, uid: UniqueId):
-        self.stream = stream
-        self.size = size
+    def __init__(self, catalog, uid: UniqueId):
         self.catalog = catalog
         self.uid = uid
         self.mode = "rb"
@@ -19,86 +14,9 @@ class AbstractCachedStream(AbstractContextManager, ABC):
         self.mode = mode
 
 
-class ProgressiveCacheStream(AbstractCachedStream):
-    BUF_SIZE = 4096
-
-    def __init__(self, stream, size, catalog, uid: UniqueId):
-        super().__init__(stream, size, catalog, uid)
-
-        self.target_path = self.catalog.cache.path_from_checksum(self.uid.get_hash())
-        self.cached_file = None
-
-        self.temp_file = None
-        self.temp_file_pos = 0
-
-    def __enter__(self):
-        if os.path.exists(self.target_path):
-            self.cached_file = open(self.target_path, mode=self.mode)
-            return self.cached_file
-
-        tmp_dir = self.catalog.cache.tmp_dir
-        if not os.path.exists(tmp_dir):
-            os.makedirs(tmp_dir)
-        self.temp_file = tempfile.NamedTemporaryFile(
-            prefix=str(self.uid.get_hash()), dir=tmp_dir, delete=False
-        )
-        return self
-
-    def __exit__(self, *args):
-        self.close()
-
-    def read(self, size=-1):
-        buf = self.stream.read(size)
-        pos = self.stream.tell()
-
-        if pos >= self.temp_file_pos:
-            self._cache_catch_up(pos, buf)
-
-        return buf
-
-    def close(self):
-        if self.cached_file:
-            self.cached_file.close()
-
-        if self.temp_file:
-            if self.temp_file_pos < self.size:
-                self._cache_catch_up(self.size)
-
-            self.temp_file.close()
-            if not os.path.exists(self.target_path):
-                os.makedirs(os.path.dirname(self.target_path), exist_ok=True)
-                shutil.move(self.temp_file.name, self.target_path)
-
-            self.stream.close()
-
-    def _cache_catch_up(self, pos_target, latest_buf=None):
-        pos_to_restore = self.stream.tell()
-        try:
-            remainder = pos_target - self.temp_file_pos
-            self.stream.seek(self.temp_file_pos)
-            while remainder > 0:
-                chunk_size = min(self.BUF_SIZE, remainder)
-                buf = self.stream.read(chunk_size)
-                self._cache_update(buf)
-                remainder -= len(buf)
-        finally:
-            self.stream.seek(pos_to_restore)
-
-    def _cache_update(self, buf):
-        length = len(buf)
-        self.temp_file.write(buf)
-        self.temp_file_pos += length
-
-    def seek(self, offset, whence=0):
-        return self.stream.seek(offset, whence)
-
-    def tell(self):
-        return self.stream.tell()
-
-
 class PreCachedStream(AbstractCachedStream):
-    def __init__(self, stream, size, catalog, uid: UniqueId):
-        super().__init__(stream, size, catalog, uid)
+    def __init__(self, catalog, uid: UniqueId):
+        super().__init__(catalog, uid)
         self.client = self.catalog.get_client(self.uid.storage)
         self.cached_file = None
 

datachain/lib/dc.py

@@ -39,6 +39,8 @@ if TYPE_CHECKING:
     import pandas as pd
     from typing_extensions import Self
 
+    from datachain.catalog import Catalog
+
 C = Column
 
 
@@ -200,10 +202,12 @@ class DataChain(DatasetQuery):
     def from_storage(
         cls,
         path,
+        *,
         type: Literal["binary", "text", "image"] = "binary",
+        catalog: Optional["Catalog"] = None,
         recursive: Optional[bool] = True,
         anon: bool = False,
-    ) -> "DataChain":
+    ) -> "Self":
         """Get data from a storage as a list of file with all file attributes. It
         returns the chain itself as usual.
 
@@ -220,7 +224,7 @@ class DataChain(DatasetQuery):
             ```
         """
         func = get_file(type)
-        return DataChain(path, recursive=recursive, anon=anon).map(file=func)
+        return cls(path, catalog=catalog, recursive=recursive, anon=anon).map(file=func)
 
     @classmethod
     def from_dataset(cls, name: str, version: Optional[int] = None) -> "DataChain":

datachain/lib/feature.py

@@ -7,6 +7,7 @@ from datetime import datetime
 from functools import lru_cache
 from types import GenericAlias
 from typing import (
+    TYPE_CHECKING,
     Any,
     ClassVar,
     Literal,
@@ -39,6 +40,9 @@ from datachain.sql.types import (
     String,
 )
 
+if TYPE_CHECKING:
+    from datachain.catalog import Catalog
+
 FeatureStandardType = Union[
     type[int],
     type[str],
@@ -158,7 +162,7 @@ class Feature(BaseModel):
         s1 = re.sub("(.)([A-Z][a-z]+)", r"\1_\2", name)
         return re.sub("([a-z0-9])([A-Z])", r"\1_\2", s1).lower()
 
-    def _set_stream(self, catalog, stream=None, caching_enabled: bool = False) -> None:
+    def _set_stream(self, catalog: "Catalog", caching_enabled: bool = False) -> None:
         pass
 
     @classmethod

datachain/lib/feature_registry.py

@@ -1,6 +1,7 @@
+import logging
 from typing import Any, ClassVar, Optional
 
-from datachain.cli import logger
+logger = logging.getLogger(__name__)
 
 
 class Registry:
@@ -16,7 +17,7 @@ class Registry:
         version = fr._version  # type: ignore[attr-defined]
         if version in cls.reg[name]:
             full_name = f"{name}@{version}"
-            logger.warning(f"Feature {full_name} is already registered")
+            logger.warning("Feature %s is already registered", full_name)
         cls.reg[name][version] = fr
 
     @classmethod

datachain/lib/file.py

@@ -2,11 +2,10 @@ import json
 from abc import ABC, abstractmethod
 from datetime import datetime
 from pathlib import Path
-from typing import Any, ClassVar, Literal, Optional, Union
+from typing import TYPE_CHECKING, Any, ClassVar, Literal, Optional, Union
 from urllib.parse import unquote, urlparse
 from urllib.request import url2pathname
 
-from fsspec import Callback
 from fsspec.implementations.local import LocalFileSystem
 from pydantic import Field, field_validator
 
@@ -18,6 +17,9 @@ from datachain.lib.utils import DataChainError
 from datachain.sql.types import JSON, Int, String
 from datachain.utils import TIME_ZERO
 
+if TYPE_CHECKING:
+    from datachain.catalog import Catalog
+
 
 class FileFeature(Feature):
     _is_file = True
@@ -182,26 +184,17 @@ class File(FileFeature):
 
     def open(self):
         if self._stream is None:
-            if self._catalog is None:
-                raise FileError(self, "stream is not set")
-            self._stream = self._open_stream()
+            raise FileError(self, "stream is not set")
 
         if self.location:
             return VFileRegistry.resolve(self, self.location)
 
         return self._stream
 
-    def _set_stream(
-        self, catalog=None, stream=None, caching_enabled: bool = False
-    ) -> None:
-        if self._catalog is None and catalog is None:
-            raise DataChainError(f"Cannot set file '{stream}' without catalog")
-
-        if catalog:
-            self._catalog = catalog
-
+    def _set_stream(self, catalog: "Catalog", caching_enabled: bool = False) -> None:
+        self._catalog = catalog
         stream_class = PreCachedStream if caching_enabled else PreDownloadStream
-        self._stream = stream_class(stream, self.size, self._catalog, self.get_uid())
+        self._stream = stream_class(self._catalog, self.get_uid())
         self._caching_enabled = caching_enabled
 
     def get_uid(self) -> UniqueId:
@@ -232,11 +225,6 @@ class File(FileFeature):
     def get_uri(self):
         return f"{self.source}/{self.get_full_name()}"
 
-    def _open_stream(self, cache: bool = False, cb: Optional[Callback] = None):
-        client = self._catalog.get_client(self.source)
-        uid = self.get_uid()
-        return client.open_object(uid, use_cache=cache, cb=cb)
-
     def get_path(self) -> str:
         path = unquote(self.get_uri())
         fs = self.get_fs()
@@ -258,10 +246,8 @@ class TextFile(File):
         super().__init__(**kwargs)
         self._stream = None
 
-    def _set_stream(
-        self, catalog=None, stream=None, caching_enabled: bool = False
-    ) -> None:
-        super()._set_stream(catalog, stream, caching_enabled)
+    def _set_stream(self, catalog: "Catalog", caching_enabled: bool = False) -> None:
+        super()._set_stream(catalog, caching_enabled)
         self._stream.set_mode("r")
 
 

datachain/lib/udf.py

@@ -6,10 +6,10 @@ from typing import TYPE_CHECKING, Callable, Optional
 from datachain.lib.feature import Feature
 from datachain.lib.signal_schema import SignalSchema
 from datachain.lib.utils import DataChainError, DataChainParamsError
-from datachain.query import Stream, udf
+from datachain.query import udf
 
 if TYPE_CHECKING:
-    from dvxc.query.udf import UDFWrapper
+    from datachain.query.udf import UDFWrapper
 
 
 class UdfError(DataChainParamsError):
@@ -34,11 +34,6 @@ class UDFBase:
 
         params_spec = params.to_udf_spec()
         self.params_spec = list(params_spec.keys())
-        self._contains_stream = False
-        if params.contains_file():
-            self.params_spec.insert(0, Stream())  # type: ignore[arg-type]
-            self._contains_stream = True
-
         self.output_spec = output.to_udf_spec()
 
         self._catalog = None
@@ -122,18 +117,10 @@ class UDFBase:
             rows = [rows]
         objs = []
         for row in rows:
-            if self._contains_stream:
-                stream, *row = row
-            else:
-                stream = None
-
             obj_row = self.params.row_to_objs(row)
-
-            if self._contains_stream:
-                for obj in obj_row:
-                    if isinstance(obj, Feature):
-                        obj._set_stream(self._catalog, stream, True)
-
+            for obj in obj_row:
+                if isinstance(obj, Feature):
+                    obj._set_stream(self._catalog, caching_enabled=True)
             objs.append(obj_row)
         return objs
 
@@ -150,13 +137,7 @@ class UDFBase:
             output_map[name] = []
 
         for flat_obj in group:
-            if self._contains_stream:
-                position = 1
-                stream = flat_obj[0]
-            else:
-                position = 0
-                stream = None
-
+            position = 0
             for signal, (cls, length) in spec_map.items():
                 slice = flat_obj[position : position + length]
                 position += length
@@ -167,7 +148,7 @@ class UDFBase:
                     obj = slice[0]
 
                 if isinstance(obj, Feature):
-                    obj._set_stream(self._catalog, stream)
+                    obj._set_stream(self._catalog)
                 output_map[signal].append(obj)
 
         return list(output_map.values())

datachain/query/dataset.py

@@ -1737,22 +1737,16 @@ class DatasetQuery:
 
             # Exclude the id column and let the db create it to avoid unique
             # constraint violations.
-            cols = [col.name for col in dr.get_table().c if col.name != "id"]
-            assert cols
             q = query.exclude(("id",))
-
             if q._order_by_clauses:
                 # ensuring we have id sorted by order by clause if it exists in a query
                 q = q.add_columns(
                     f.row_number().over(order_by=q._order_by_clauses).label("id")
                 )
-                cols.append("id")
-
-            self.catalog.warehouse.db.execute(
-                sqlalchemy.insert(dr.get_table()).from_select(cols, q),
-                **kwargs,
-            )
 
+            cols = tuple(c.name for c in q.columns)
+            insert_q = sqlalchemy.insert(dr.get_table()).from_select(cols, q)
+            self.catalog.warehouse.db.execute(insert_q, **kwargs)
             self.catalog.metastore.update_dataset_status(
                 dataset, DatasetStatus.COMPLETE, version=version
             )

datachain/sql/sqlite/base.py

@@ -71,8 +71,6 @@ def setup():
     compiles(sql_path.name, "sqlite")(compile_path_name)
     compiles(sql_path.file_stem, "sqlite")(compile_path_file_stem)
     compiles(sql_path.file_ext, "sqlite")(compile_path_file_ext)
-    compiles(array.cosine_distance, "sqlite")(compile_cosine_distance)
-    compiles(array.euclidean_distance, "sqlite")(compile_euclidean_distance)
     compiles(array.length, "sqlite")(compile_array_length)
     compiles(string.length, "sqlite")(compile_string_length)
     compiles(string.split, "sqlite")(compile_string_split)
@@ -81,6 +79,13 @@ def setup():
     compiles(Values, "sqlite")(compile_values)
     compiles(random.rand, "sqlite")(compile_rand)
 
+    if load_usearch_extension(sqlite3.connect(":memory:")):
+        compiles(array.cosine_distance, "sqlite")(compile_cosine_distance_ext)
+        compiles(array.euclidean_distance, "sqlite")(compile_euclidean_distance_ext)
+    else:
+        compiles(array.cosine_distance, "sqlite")(compile_cosine_distance)
+        compiles(array.euclidean_distance, "sqlite")(compile_euclidean_distance)
+
     register_user_defined_sql_functions()
     setup_is_complete = True
 
@@ -246,11 +251,23 @@ def compile_path_file_ext(element, compiler, **kwargs):
     return compiler.process(path_file_ext(*element.clauses.clauses), **kwargs)
 
 
+def compile_cosine_distance_ext(element, compiler, **kwargs):
+    run_compiler_hook("cosine_distance")
+    return f"distance_cosine_f32({compiler.process(element.clauses, **kwargs)})"
+
+
 def compile_cosine_distance(element, compiler, **kwargs):
     run_compiler_hook("cosine_distance")
     return f"cosine_distance({compiler.process(element.clauses, **kwargs)})"
 
 
+def compile_euclidean_distance_ext(element, compiler, **kwargs):
+    run_compiler_hook("euclidean_distance")
+    return (
+        f"sqrt(distance_sqeuclidean_f32({compiler.process(element.clauses, **kwargs)}))"
+    )
+
+
 def compile_euclidean_distance(element, compiler, **kwargs):
     run_compiler_hook("euclidean_distance")
     return f"euclidean_distance({compiler.process(element.clauses, **kwargs)})"
@@ -330,3 +347,18 @@ def compile_values(element, compiler, **kwargs):
 
 def compile_rand(element, compiler, **kwargs):
     return compiler.process(func.random(), **kwargs)
+
+
+def load_usearch_extension(conn) -> bool:
+    try:
+        # usearch is part of the vector optional dependencies
+        # we use the extension's cosine and euclidean distance functions
+        from usearch import sqlite_path
+
+        conn.enable_load_extension(True)
+        conn.load_extension(sqlite_path())
+        conn.enable_load_extension(False)
+        return True
+
+    except Exception:  # noqa: BLE001
+        return False

datachain/sql/sqlite/vector.py

@@ -1,15 +1,23 @@
-import json
+import math
 
 import numpy as np
-from scipy.spatial import distance
 
 
 def euclidean_distance(a: str, b: str):
-    a_np = np.array(json.loads(a))
-    b_np = np.array(json.loads(b))
+    a_np = np.fromstring(a[1:-1], sep=",")
+    b_np = np.fromstring(b[1:-1], sep=",")
 
     return np.linalg.norm(b_np - a_np)
 
 
 def cosine_distance(a: str, b: str):
-    return distance.cosine(json.loads(a), json.loads(b))
+    u = np.fromstring(a[1:-1], sep=",")
+    v = np.fromstring(b[1:-1], sep=",")
+
+    uv = np.inner(u, v)
+    uu = np.inner(u, u)
+    vv = np.inner(v, v)
+
+    dist = 1.0 - uv / math.sqrt(uu * vv)
+
+    return max(0, min(dist, 2.0))

{datachain-0.2.0.dist-info → datachain-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.2.0
+Version: 0.2.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -79,7 +79,7 @@ Requires-Dist: open-clip-torch ; extra == 'tests'
 Requires-Dist: aiotools >=1.7.0 ; extra == 'tests'
 Requires-Dist: requests-mock ; extra == 'tests'
 Provides-Extra: vector
-Requires-Dist: scipy ; extra == 'vector'
+Requires-Dist: usearch ; extra == 'vector'
 
 |PyPI| |Python Version| |Codecov| |Tests| |License|
 

{datachain-0.2.0.dist-info → datachain-0.2.1.dist-info}/RECORD

@@ -1,9 +1,8 @@
-datachain/__init__.py,sha256=9a0qX6tqyA9KC3ahLmGarqlRTZJXhM7HijAWpfUaOnQ,102
+datachain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
-datachain/_version.py,sha256=H-qsvrxCpdhaQzyddR-yajEqI71hPxLa4KxzpP3uS1g,411
 datachain/asyn.py,sha256=CKCFQJ0CbB3r04S7mUTXxriKzPnOvdUaVPXjM8vCtJw,7644
 datachain/cache.py,sha256=FaPWrqWznPffmskTb1pdPkt2jAMMf__9FC2zEnP0vDU,4022
-datachain/cli.py,sha256=FLKRimIq917Dq0EmG3yLzMTqDaMA0vyCRUREOobUspY,32256
+datachain/cli.py,sha256=lInqYMhk8YuPY-ZWkfWZmE-ZmdIChJgbs305-a_MWpo,32457
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=PfC7W5yO6HFO6-iMB4YB-0RR88LPiGmD6sS_SfVbGso,1979
 datachain/dataset.py,sha256=MZezyuJWNj_3PEtzr0epPMNyWAOTrhTSPI5FmemV6L4,14470
@@ -33,19 +32,19 @@ datachain/data_storage/db_engine.py,sha256=mxOoWP4ntBMgLeTAk4dlEeIJArAz4x_tFrHyt
 datachain/data_storage/id_generator.py,sha256=VlDALKijggegAnNMJwuMETJgnLoPYxpkrkld5DNTPQw,3839
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
 datachain/data_storage/metastore.py,sha256=y-4fYvuOPnWeYxAvqhDnw6CdlTvQiurg0Gg4TaG9LR0,54074
-datachain/data_storage/schema.py,sha256=FrhmeZ_btT1CfVisa4ScabS11ixZ3xn3d_whvVsBtDA,8700
+datachain/data_storage/schema.py,sha256=t58LexPOCam_vWV0W52otEDNXgtFPHX3QFApEncFy2s,8809
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=eHTiJ0VIxU-chnhKNTN14EsaSnw5LAaxTLi9aMCZpl4,24978
+datachain/data_storage/sqlite.py,sha256=F68Q_AIqNAObZ5kJ0GnBqRC6e2D2sRehkQo8UzrHgtI,25079
 datachain/data_storage/warehouse.py,sha256=tL2mYoXVZe-coKLTRXEJ0sMdEr2BD0GwgIWip5PP5CM,33300
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/arrow.py,sha256=7lAas8hSh3vL7S7s2KOlkYn4viQpfVbM_FQ_hLCh5oc,2593
-datachain/lib/cached_stream.py,sha256=BQI6gpJ2y7_-jqQo_0VB9ntbkOVISvj9wlDwGDQbqw8,3537
+datachain/lib/cached_stream.py,sha256=t2ifK0hZVZiVn0MQ8D3FaFK1-qK84TwJW2Dw1SRsw9g,1066
 datachain/lib/claude.py,sha256=iAauA1zNVNONpLzUo1t0QN5PZ5Ot6cZkfib7Ka_c638,1969
-datachain/lib/dc.py,sha256=szYQC4FOoYDMlSEDAPWZ25z4Nn-WeoaKiqKwwXbOJws,35355
-datachain/lib/feature.py,sha256=KiPiMrU8ec-bJuUs70Xh4jytZdzKk9puQNQnx03K-po,12057
-datachain/lib/feature_registry.py,sha256=YQsLYChNkYK6p2MpcVfAyBybtfN5EMiOJ8LIYakjmeQ,1602
+datachain/lib/dc.py,sha256=PBbEZhSPnbvB6jh2eTgZyDSouAGbjgEv8xabW45_vmk,35460
+datachain/lib/feature.py,sha256=QDloA9HE7URf9J_veKrguYBvSg-0cbXZFTswNxrKsB8,12135
+datachain/lib/feature_registry.py,sha256=K3jGQzBp2HZDjR9hdGe1BZaXOAne8RpkCRRQdTVjkTs,1622
 datachain/lib/feature_utils.py,sha256=LIK233IWGWFhuav5Rm8de0xIOSnuwA1ubk6OYrxrfN0,4712
-datachain/lib/file.py,sha256=K0jH8Q5Xle2TiVDTCzmopku_7Lh-IVufV_mgtaCNHYI,8744
+datachain/lib/file.py,sha256=GQrqGgCEHICrUTdzTz_yhXqJWiae9EPTte1sd3hKeEU,8246
 datachain/lib/gpt4_vision.py,sha256=idyXVZVWzltstGaVIu5RYE5UNbdqcPEjIWy81O1MwkM,2922
 datachain/lib/hf_image_to_text.py,sha256=HiPSWzJRDT-vnz9DXJbJBNCMNl9wmpxiSS3PbbVz8SE,3310
 datachain/lib/hf_pipeline.py,sha256=f0AH_XCziOF1OKN3d1w1swTBLaeajMJ8xgdsX37i5-o,2287
@@ -58,7 +57,7 @@ datachain/lib/reader.py,sha256=rPXXNoTUdm6PQwkAlaU-nOBreP_q4ett_EjFStrA_W0,1727
 datachain/lib/settings.py,sha256=6Nkoh8riETrftYwDp3aniK53Dsjc07MdztL8N0cW1D8,2849
 datachain/lib/signal_schema.py,sha256=KaH194dAH8Zt8FtlNAgdVqcZlJc42y7RbcB37ldPPAY,11688
 datachain/lib/text.py,sha256=EEZrYohADi5rAGg3aLLRwtvyAV9js_yWAGhr2C3QbwI,2424
-datachain/lib/udf.py,sha256=kPc_6fQ4DzbiYiXvbps7QPlJWTu9MSCS8eUfGqOhjG4,6124
+datachain/lib/udf.py,sha256=D9TMxkAvj3zPRnZmkCxadEDtiG3B45t2xAEpuO14MOQ,5600
 datachain/lib/udf_signature.py,sha256=DAWMQ0dvFkKabpY5MV5K2q9YmOSTKfiV8KuUBs_6kMg,7258
 datachain/lib/unstructured.py,sha256=9Y6rAelXdYqkNbPaqz6DhXjhS8d6qXcP0ieIsWkzvkk,1143
 datachain/lib/utils.py,sha256=YQKzuW096SGe7QwHwdyS47k_9l2Rh73b-wBqt1-niw4,213
@@ -68,7 +67,7 @@ datachain/lib/webdataset_laion.py,sha256=HAtSCbVvEQqzKkoRamRxDKaQALSB3QmJRU2yWRF
 datachain/query/__init__.py,sha256=tv-spkjUCYamMN9ys_90scYrZ8kJ7C7d1MTYVmxGtk4,325
 datachain/query/batch.py,sha256=sOMxXbaNii7lVyFIEZ2noqbhy_S8qtZ-WWxrka72shc,3474
 datachain/query/builtins.py,sha256=ZKNs49t8Oa_OaboCBIEqtXZt7c1Qe9OR_C_HpoDriIU,2781
-datachain/query/dataset.py,sha256=c0ZoNEjAMmn0BdSnRm8XRWEsbaMH3xa_jd6FBJQDY1o,64576
+datachain/query/dataset.py,sha256=QYrtZApS8djybkuDfGO0tt8O6sCBlmkg9TE__R4eM-I,64475
 datachain/query/dispatch.py,sha256=fEk1qalxAb5JJhN-iq0Mg9MyWve4XoN1Q7uvrX4mJY4,13106
 datachain/query/metrics.py,sha256=vsECqbZfoSDBnvC3GQlziKXmISVYDLgHP1fMPEOtKyo,640
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -90,12 +89,12 @@ datachain/sql/functions/path.py,sha256=zixpERotTFP6LZ7I4TiGtyRA8kXOoZmH1yzH9oRW0
 datachain/sql/functions/random.py,sha256=vBwEEj98VH4LjWixUCygQ5Bz1mv1nohsCG0-ZTELlVg,271
 datachain/sql/functions/string.py,sha256=DsyY6ZMAUqmZVRSla-BJLsLYNsIgLOh4XLR3yvYJUbE,505
 datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7d04,166
-datachain/sql/sqlite/base.py,sha256=XVxn4pB-N4pPfiby5uVvfH7feNzRKlBNzsc5eyKPvhI,10965
+datachain/sql/sqlite/base.py,sha256=nPMF6_FF04hclDNZev_YfxMgbJAsWEdF-rU2pUhqBtc,12048
 datachain/sql/sqlite/types.py,sha256=oP93nLfTBaYnN0z_4Dsv-HZm8j9rrUf1esMM-z3JLbg,1754
-datachain/sql/sqlite/vector.py,sha256=stBeEW6fbVbILmAtV4khjXdJIGT13HkRWJeCoqIOk50,315
-datachain-0.2.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.2.0.dist-info/METADATA,sha256=iMX8hWEMXu-4MtXlD_SVwW3ija6bOLqSbeQvHoiMNfQ,14344
-datachain-0.2.0.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
-datachain-0.2.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.2.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.2.0.dist-info/RECORD,,
+datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
+datachain-0.2.1.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.2.1.dist-info/METADATA,sha256=kgX6auIOqU0DtW6dRyGWs1TrlGYLf1kN_By0XFW3t0Q,14346
+datachain-0.2.1.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+datachain-0.2.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.2.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.2.1.dist-info/RECORD,,

datachain/_version.py

@@ -1,16 +0,0 @@
-# file generated by setuptools_scm
-# don't change, don't track in version control
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple, Union
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-else:
-    VERSION_TUPLE = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-
-__version__ = version = '0.2.0'
-__version_tuple__ = version_tuple = (0, 2, 0)