datachain 0.2.8__py3-none-any.whl → 0.2.10__py3-none-any.whl

datachain/node.py

@@ -46,8 +46,8 @@ class DirTypeGroup:
 
 @attrs.define
 class Node:
-    id: int = 0
-    random: int = -1
+    sys__id: int = 0
+    sys__rand: int = -1
     vtype: str = ""
     dir_type: Optional[int] = None
     parent: str = ""
@@ -127,11 +127,11 @@ class Node:
 
     @classmethod
     def from_dir(cls, parent, name, **kwargs) -> "Node":
-        return cls(id=-1, dir_type=DirType.DIR, parent=parent, name=name, **kwargs)
+        return cls(sys__id=-1, dir_type=DirType.DIR, parent=parent, name=name, **kwargs)
 
     @classmethod
     def root(cls) -> "Node":
-        return cls(-1, dir_type=DirType.DIR)
+        return cls(sys__id=-1, dir_type=DirType.DIR)
 
 
 @attrs.define

datachain/query/batch.py

@@ -104,7 +104,7 @@ class Partition(BatchingStrategy):
         with contextlib.closing(
             execute(
                 query,
-                order_by=(PARTITION_COLUMN_ID, "id", *query._order_by_clauses),
+                order_by=(PARTITION_COLUMN_ID, "sys__id", *query._order_by_clauses),
                 limit=query._limit,
             )
         ) as rows:

datachain/query/dataset.py

@@ -31,6 +31,7 @@ import sqlalchemy
 from attrs import frozen
 from dill import dumps, source
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback, TqdmCallback
+from pydantic import BaseModel
 from sqlalchemy import Column
 from sqlalchemy.sql import func as f
 from sqlalchemy.sql.elements import ColumnClause, ColumnElement
@@ -57,7 +58,6 @@ from datachain.sql.functions import rand
 from datachain.storage import Storage, StorageURI
 from datachain.utils import batched, determine_processes, inside_notebook
 
-from .batch import RowBatch
 from .metrics import metrics
 from .schema import C, UDFParamSpec, normalize_param
 from .session import Session
@@ -257,7 +257,7 @@ class DatasetDiffOperation(Step):
         """
 
     def apply(self, query_generator, temp_tables: list[str]):
-        source_query = query_generator.exclude(("id",))
+        source_query = query_generator.exclude(("sys__id",))
         target_query = self.dq.apply_steps().select()
         temp_tables.extend(self.dq.temp_table_names)
 
@@ -427,22 +427,6 @@ def get_generated_callback(is_generator: bool = False) -> Callback:
     return DEFAULT_CALLBACK
 
 
-def run_udf(
-    udf,
-    udf_inputs,
-    catalog,
-    is_generator,
-    cache,
-    download_cb: Callback = DEFAULT_CALLBACK,
-    processed_cb: Callback = DEFAULT_CALLBACK,
-) -> Iterator[Iterable["UDFResult"]]:
-    for batch in udf_inputs:
-        n_rows = len(batch.rows) if isinstance(batch, RowBatch) else 1
-        output = udf(catalog, batch, is_generator, cache, cb=download_cb)
-        processed_cb.relative_update(n_rows)
-        yield output
-
-
 @frozen
 class UDF(Step, ABC):
     udf: UDFType
@@ -548,9 +532,6 @@ class UDF(Step, ABC):
                 else:
                     udf = self.udf
 
-                if hasattr(udf.func, "setup") and callable(udf.func.setup):
-                    udf.func.setup()
-
                 warehouse = self.catalog.warehouse
 
                 with contextlib.closing(
@@ -560,8 +541,7 @@ class UDF(Step, ABC):
                     processed_cb = get_processed_callback()
                     generated_cb = get_generated_callback(self.is_generator)
                     try:
-                        udf_results = run_udf(
-                            udf,
+                        udf_results = udf.run(
                             udf_inputs,
                             self.catalog,
                             self.is_generator,
@@ -583,9 +563,6 @@ class UDF(Step, ABC):
 
                 warehouse.insert_rows_done(udf_table)
 
-                if hasattr(udf.func, "teardown") and callable(udf.func.teardown):
-                    udf.func.teardown()
-
         except QueryScriptCancelError:
             self.catalog.warehouse.close()
             sys.exit(QUERY_SCRIPT_CANCELED_EXIT_CODE)
@@ -663,7 +640,7 @@ class UDF(Step, ABC):
 
         # fill table with partitions
         cols = [
-            query.selected_columns.id,
+            query.selected_columns.sys__id,
             f.dense_rank().over(order_by=list_partition_by).label(PARTITION_COLUMN_ID),
         ]
         self.catalog.warehouse.db.execute(
@@ -697,7 +674,7 @@ class UDF(Step, ABC):
             subq = query.subquery()
             query = (
                 sqlalchemy.select(*subq.c)
-                .outerjoin(partition_tbl, partition_tbl.c.id == subq.c.id)
+                .outerjoin(partition_tbl, partition_tbl.c.sys__id == subq.c.sys__id)
                 .add_columns(*partition_columns())
             )
 
@@ -729,18 +706,18 @@ class UDFSignal(UDF):
         columns = [
             sqlalchemy.Column(c.name, c.type)
             for c in query.selected_columns
-            if c.name != "id"
+            if c.name != "sys__id"
         ]
         table = self.catalog.warehouse.create_udf_table(self.udf_table_name(), columns)
         select_q = query.with_only_columns(
-            *[c for c in query.selected_columns if c.name != "id"]
+            *[c for c in query.selected_columns if c.name != "sys__id"]
         )
 
         # if there is order by clause we need row_number to preserve order
         # if there is no order by clause we still need row_number to generate
         # unique ids as uniqueness is important for this table
         select_q = select_q.add_columns(
-            f.row_number().over(order_by=select_q._order_by_clauses).label("id")
+            f.row_number().over(order_by=select_q._order_by_clauses).label("sys__id")
         )
 
         self.catalog.warehouse.db.execute(
@@ -756,7 +733,7 @@ class UDFSignal(UDF):
         if query._order_by_clauses:
             # we are adding ordering only if it's explicitly added by user in
             # query part before adding signals
-            q = q.order_by(table.c.id)
+            q = q.order_by(table.c.sys__id)
         return q, [table]
 
     def create_result_query(
@@ -766,7 +743,7 @@ class UDFSignal(UDF):
         original_cols = [c for c in subq.c if c.name not in partition_col_names]
 
         # new signal columns that are added to udf_table
-        signal_cols = [c for c in udf_table.c if c.name != "id"]
+        signal_cols = [c for c in udf_table.c if c.name != "sys__id"]
         signal_name_cols = {c.name: c for c in signal_cols}
         cols = signal_cols
 
@@ -786,7 +763,7 @@ class UDFSignal(UDF):
                 res = (
                     sqlalchemy.select(*cols1)
                     .select_from(subq)
-                    .outerjoin(udf_table, udf_table.c.id == subq.c.id)
+                    .outerjoin(udf_table, udf_table.c.sys__id == subq.c.sys__id)
                     .add_columns(*cols2)
                 )
             else:
@@ -795,7 +772,7 @@ class UDFSignal(UDF):
             if query._order_by_clauses:
                 # if ordering is used in query part before adding signals, we
                 # will have it as order by id from select from pre-created udf table
-                res = res.order_by(subq.c.id)
+                res = res.order_by(subq.c.sys__id)
 
             if self.partition_by is not None:
                 subquery = res.subquery()
@@ -833,7 +810,7 @@ class RowGenerator(UDF):
             # we get the same rows as we got as inputs of UDF since selecting
             # without ordering can be non deterministic in some databases
             c = query.selected_columns
-            query = query.order_by(c.id)
+            query = query.order_by(c.sys__id)
 
         udf_table_query = udf_table.select().subquery()
         udf_table_cols: list[sqlalchemy.Label[Any]] = [
@@ -1025,7 +1002,7 @@ class SQLJoin(Step):
         q1_column_names = {c.name for c in q1_columns}
         q2_columns = [
             c
-            if c.name not in q1_column_names and c.name != "id"
+            if c.name not in q1_column_names and c.name != "sys__id"
             else c.label(self.rname.format(name=c.name))
             for c in q2.c
         ]
@@ -1165,8 +1142,8 @@ class DatasetQuery:
             self.version = version or ds.latest_version
             self.feature_schema = ds.get_version(self.version).feature_schema
             self.column_types = copy(ds.schema)
-            if "id" in self.column_types:
-                self.column_types.pop("id")
+            if "sys__id" in self.column_types:
+                self.column_types.pop("sys__id")
             self.starting_step = QueryStep(self.catalog, name, self.version)
             # attaching to specific dataset
             self.name = name
@@ -1239,7 +1216,7 @@ class DatasetQuery:
             query.steps = self._chunk_limit(query.steps, index, total)
 
             # Prepend the chunk filter to the step chain.
-            query = query.filter(C.random % total == index)
+            query = query.filter(C.sys__rand % total == index)
             query.steps = query.steps[-1:] + query.steps[:-1]
 
         result = query.starting_step.apply()
@@ -1366,10 +1343,8 @@ class DatasetQuery:
         finally:
             self.cleanup()
 
-    def to_records(self) -> list[dict]:
-        with self.as_iterable() as result:
-            cols = result.columns
-            return [dict(zip(cols, row)) for row in result]
+    def to_records(self) -> list[dict[str, Any]]:
+        return self.results(lambda cols, row: dict(zip(cols, row)))
 
     def to_pandas(self) -> "pd.DataFrame":
         records = self.to_records()
@@ -1379,7 +1354,7 @@ class DatasetQuery:
 
     def shuffle(self) -> "Self":
         # ToDo: implement shaffle based on seed and/or generating random column
-        return self.order_by(C.random)
+        return self.order_by(C.sys__rand)
 
     def sample(self, n) -> "Self":
         """
@@ -1508,30 +1483,35 @@ class DatasetQuery:
         query.steps.append(SQLOffset(offset))
         return query
 
+    def as_scalar(self) -> Any:
+        with self.as_iterable() as rows:
+            row = next(iter(rows))
+        return row[0]
+
     def count(self) -> int:
         query = self.clone()
         query.steps.append(SQLCount())
-        return query.results()[0][0]
+        return query.as_scalar()
 
-    def sum(self, col: ColumnElement):
+    def sum(self, col: ColumnElement) -> int:
         query = self.clone()
         query.steps.append(SQLSelect((f.sum(col),)))
-        return query.results()[0][0]
+        return query.as_scalar()
 
-    def avg(self, col: ColumnElement):
+    def avg(self, col: ColumnElement) -> int:
         query = self.clone()
         query.steps.append(SQLSelect((f.avg(col),)))
-        return query.results()[0][0]
+        return query.as_scalar()
 
-    def min(self, col: ColumnElement):
+    def min(self, col: ColumnElement) -> int:
         query = self.clone()
         query.steps.append(SQLSelect((f.min(col),)))
-        return query.results()[0][0]
+        return query.as_scalar()
 
-    def max(self, col: ColumnElement):
+    def max(self, col: ColumnElement) -> int:
         query = self.clone()
         query.steps.append(SQLSelect((f.max(col),)))
-        return query.results()[0][0]
+        return query.as_scalar()
 
     @detach
     def group_by(self, *cols: ColumnElement) -> "Self":
@@ -1723,7 +1703,7 @@ class DatasetQuery:
                 c if isinstance(c, Column) else Column(c.name, c.type)
                 for c in query.columns
             ]
-            if not [c for c in columns if c.name != "id"]:
+            if not [c for c in columns if c.name != "sys__id"]:
                 raise RuntimeError(
                     "No columns to save in the query. "
                     "Ensure at least one column (other than 'id') is selected."
@@ -1742,11 +1722,11 @@ class DatasetQuery:
 
             # Exclude the id column and let the db create it to avoid unique
             # constraint violations.
-            q = query.exclude(("id",))
+            q = query.exclude(("sys__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")
+                    f.row_number().over(order_by=q._order_by_clauses).label("sys__id")
                 )
 
             cols = tuple(c.name for c in q.columns)
@@ -1876,9 +1856,9 @@ def _random_string(length: int) -> str:
 
 
 def _feature_predicate(obj):
-    from datachain.lib.feature import Feature
-
-    return inspect.isclass(obj) and source.isfrommain(obj) and issubclass(obj, Feature)
+    return (
+        inspect.isclass(obj) and source.isfrommain(obj) and issubclass(obj, BaseModel)
+    )
 
 
 def _imports(obj):

datachain/query/dispatch.py

@@ -16,7 +16,6 @@ from multiprocess import get_context
 
 from datachain.catalog import Catalog
 from datachain.catalog.loader import get_distributed_class
-from datachain.query.batch import RowBatch
 from datachain.query.dataset import (
     get_download_callback,
     get_generated_callback,
@@ -355,6 +354,15 @@ class WorkerCallback(Callback):
         put_into_queue(self.queue, {"status": NOTIFY_STATUS, "downloaded": inc})
 
 
+class ProcessedCallback(Callback):
+    def __init__(self):
+        self.processed_rows: Optional[int] = None
+        super().__init__()
+
+    def relative_update(self, inc: int = 1) -> None:
+        self.processed_rows = inc
+
+
 @attrs.define
 class UDFWorker:
     catalog: Catalog
@@ -370,25 +378,28 @@ class UDFWorker:
         return WorkerCallback(self.done_queue)
 
     def run(self) -> None:
-        if hasattr(self.udf.func, "setup") and callable(self.udf.func.setup):
-            self.udf.func.setup()
-        while (batch := get_from_queue(self.task_queue)) != STOP_SIGNAL:
-            n_rows = len(batch.rows) if isinstance(batch, RowBatch) else 1
-            udf_output = self.udf(
-                self.catalog,
-                batch,
-                is_generator=self.is_generator,
-                cache=self.cache,
-                cb=self.cb,
-            )
+        processed_cb = ProcessedCallback()
+        udf_results = self.udf.run(
+            self.get_inputs(),
+            self.catalog,
+            self.is_generator,
+            self.cache,
+            download_cb=self.cb,
+            processed_cb=processed_cb,
+        )
+        for udf_output in udf_results:
             if isinstance(udf_output, GeneratorType):
                 udf_output = list(udf_output)  # can not pickle generator
             put_into_queue(
                 self.done_queue,
-                {"status": OK_STATUS, "result": udf_output, "processed": n_rows},
+                {
+                    "status": OK_STATUS,
+                    "result": udf_output,
+                    "processed": processed_cb.processed_rows,
+                },
             )
-
-        if hasattr(self.udf.func, "teardown") and callable(self.udf.func.teardown):
-            self.udf.func.teardown()
-
         put_into_queue(self.done_queue, {"status": FINISHED_STATUS})
+
+    def get_inputs(self):
+        while (batch := get_from_queue(self.task_queue)) != STOP_SIGNAL:
+            yield batch

datachain/query/udf.py

@@ -1,5 +1,5 @@
 import typing
-from collections.abc import Iterable, Mapping, Sequence
+from collections.abc import Iterable, Iterator, Mapping, Sequence
 from dataclasses import dataclass
 from functools import WRAPPER_ASSIGNMENTS
 from inspect import isclass
@@ -14,7 +14,6 @@ from typing import (
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
 
 from datachain.dataset import RowDict
-from datachain.lib.utils import AbstractUDF
 
 from .batch import Batch, BatchingStrategy, NoBatching, Partition, RowBatch
 from .schema import (
@@ -100,15 +99,28 @@ class UDFBase:
 
     def __init__(
         self,
-        func: Callable,
         properties: UDFProperties,
     ):
-        self.func = func
         self.properties = properties
         self.signal_names = properties.signal_names()
         self.output = properties.output
 
-    def __call__(
+    def run(
+        self,
+        udf_inputs: "Iterable[BatchingResult]",
+        catalog: "Catalog",
+        is_generator: bool,
+        cache: bool,
+        download_cb: Callback = DEFAULT_CALLBACK,
+        processed_cb: Callback = DEFAULT_CALLBACK,
+    ) -> Iterator[Iterable["UDFResult"]]:
+        for batch in udf_inputs:
+            n_rows = len(batch.rows) if isinstance(batch, RowBatch) else 1
+            output = self.run_once(catalog, batch, is_generator, cache, cb=download_cb)
+            processed_cb.relative_update(n_rows)
+            yield output
+
+    def run_once(
         self,
         catalog: "Catalog",
         arg: "BatchingResult",
@@ -116,24 +128,7 @@ class UDFBase:
         cache: bool = False,
         cb: Callback = DEFAULT_CALLBACK,
     ) -> Iterable[UDFResult]:
-        if isinstance(self.func, AbstractUDF):
-            self.func._catalog = catalog  # type: ignore[unreachable]
-
-        if isinstance(arg, RowBatch):
-            udf_inputs = [
-                self.bind_parameters(catalog, row, cache=cache, cb=cb)
-                for row in arg.rows
-            ]
-            udf_outputs = self.func(udf_inputs)
-            return self._process_results(arg.rows, udf_outputs, is_generator)
-        if isinstance(arg, RowDict):
-            udf_inputs = self.bind_parameters(catalog, arg, cache=cache, cb=cb)
-            udf_outputs = self.func(*udf_inputs)
-            if not is_generator:
-                # udf_outputs is generator already if is_generator=True
-                udf_outputs = [udf_outputs]
-            return self._process_results([arg], udf_outputs, is_generator)
-        raise ValueError(f"Unexpected UDF argument: {arg}")
+        raise NotImplementedError
 
     def bind_parameters(self, catalog: "Catalog", row: "RowDict", **kwargs) -> list:
         return [p.get_value(catalog, row, **kwargs) for p in self.properties.params]
@@ -152,9 +147,9 @@ class UDFBase:
             return (dict(zip(self.signal_names, row)) for row in results)
 
         # outputting signals
-        row_ids = [row["id"] for row in rows]
+        row_ids = [row["sys__id"] for row in rows]
         return [
-            dict(id=row_id, **dict(zip(self.signal_names, signals)))
+            {"sys__id": row_id} | dict(zip(self.signal_names, signals))
             for row_id, signals in zip(row_ids, results)
             if signals is not None  # skip rows with no output
         ]
@@ -194,12 +189,37 @@ class UDFWrapper(UDFBase):
         func: Callable,
         properties: UDFProperties,
     ):
-        super().__init__(func, properties)
+        self.func = func
+        super().__init__(properties)
         # This emulates the behavior of functools.wraps for a class decorator
         for attr in WRAPPER_ASSIGNMENTS:
             if hasattr(func, attr):
                 setattr(self, attr, getattr(func, attr))
 
+    def run_once(
+        self,
+        catalog: "Catalog",
+        arg: "BatchingResult",
+        is_generator: bool = False,
+        cache: bool = False,
+        cb: Callback = DEFAULT_CALLBACK,
+    ) -> Iterable[UDFResult]:
+        if isinstance(arg, RowBatch):
+            udf_inputs = [
+                self.bind_parameters(catalog, row, cache=cache, cb=cb)
+                for row in arg.rows
+            ]
+            udf_outputs = self.func(udf_inputs)
+            return self._process_results(arg.rows, udf_outputs, is_generator)
+        if isinstance(arg, RowDict):
+            udf_inputs = self.bind_parameters(catalog, arg, cache=cache, cb=cb)
+            udf_outputs = self.func(*udf_inputs)
+            if not is_generator:
+                # udf_outputs is generator already if is_generator=True
+                udf_outputs = [udf_outputs]
+            return self._process_results([arg], udf_outputs, is_generator)
+        raise ValueError(f"Unexpected UDF argument: {arg}")
+
     # This emulates the behavior of functools.wraps for a class decorator
     def __repr__(self):
         return repr(self.func)

datachain/remote/studio.py

@@ -190,19 +190,11 @@ class StudioClient:
     def dataset_rows_chunk(
         self, name: str, version: int, offset: int
     ) -> Response[DatasetRowsData]:
-        def _parse_row(row):
-            row["id"] = int(row["id"])
-            return row
-
         req_data = {"dataset_name": name, "dataset_version": version}
-        response = self._send_request_msgpack(
+        return self._send_request_msgpack(
             "dataset-rows",
             {**req_data, "offset": offset, "limit": DATASET_ROWS_CHUNK_SIZE},
         )
-        if response.ok:
-            response.data = [_parse_row(r) for r in response.data]
-
-        return response
 
     def dataset_stats(self, name: str, version: int) -> Response[DatasetStatsData]:
         response = self._send_request(

datachain/torch/__init__.py

@@ -0,0 +1,21 @@
+try:
+    from datachain.lib.clip import similarity_scores as clip_similarity_scores
+    from datachain.lib.image import convert_image, convert_images
+    from datachain.lib.pytorch import PytorchDataset, label_to_int
+    from datachain.lib.text import convert_text
+
+except ImportError as exc:
+    raise ImportError(
+        "Missing dependencies for torch:\n"
+        "To install run:\n\n"
+        "  pip install 'datachain[torch]'\n"
+    ) from exc
+
+__all__ = [
+    "PytorchDataset",
+    "clip_similarity_scores",
+    "convert_image",
+    "convert_images",
+    "convert_text",
+    "label_to_int",
+]

{datachain-0.2.8.dist-info → datachain-0.2.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.2.8
+Version: 0.2.10
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -38,12 +38,8 @@ Requires-Dist: ujson >=5.9.0
 Requires-Dist: pydantic <3,>=2
 Requires-Dist: jmespath >=1.0
 Requires-Dist: datamodel-code-generator >=0.25
+Requires-Dist: Pillow <11,>=10.0.0
 Requires-Dist: numpy <2,>=1 ; sys_platform == "win32"
-Provides-Extra: cv
-Requires-Dist: Pillow <11,>=10.0.0 ; extra == 'cv'
-Requires-Dist: torch >=2.1.0 ; extra == 'cv'
-Requires-Dist: torchvision ; extra == 'cv'
-Requires-Dist: transformers >=4.36.0 ; extra == 'cv'
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests] ; extra == 'dev'
 Requires-Dist: mypy ==1.10.1 ; extra == 'dev'
@@ -63,7 +59,7 @@ Requires-Dist: lz4 ; extra == 'remote'
 Requires-Dist: msgpack <2,>=1.0.4 ; extra == 'remote'
 Requires-Dist: requests >=2.22.0 ; extra == 'remote'
 Provides-Extra: tests
-Requires-Dist: datachain[cv,remote,vector] ; extra == 'tests'
+Requires-Dist: datachain[remote,torch,vector] ; extra == 'tests'
 Requires-Dist: pytest <9,>=8 ; extra == 'tests'
 Requires-Dist: pytest-sugar >=0.9.6 ; extra == 'tests'
 Requires-Dist: pytest-cov >=4.1.0 ; extra == 'tests'
@@ -78,6 +74,10 @@ Requires-Dist: hypothesis ; extra == 'tests'
 Requires-Dist: open-clip-torch ; extra == 'tests'
 Requires-Dist: aiotools >=1.7.0 ; extra == 'tests'
 Requires-Dist: requests-mock ; extra == 'tests'
+Provides-Extra: torch
+Requires-Dist: torch >=2.1.0 ; extra == 'torch'
+Requires-Dist: torchvision ; extra == 'torch'
+Requires-Dist: transformers >=4.36.0 ; extra == 'torch'
 Provides-Extra: vector
 Requires-Dist: usearch ; extra == 'vector'
 
@@ -89,11 +89,11 @@ Requires-Dist: usearch ; extra == 'vector'
 .. |Python Version| image:: https://img.shields.io/pypi/pyversions/datachain
    :target: https://pypi.org/project/datachain
    :alt: Python Version
-.. |Codecov| image:: https://codecov.io/gh/iterative/dvcx/branch/main/graph/badge.svg?token=VSCP2T9R5X
-   :target: https://app.codecov.io/gh/iterative/dvcx
+.. |Codecov| image:: https://codecov.io/gh/iterative/datachain/graph/badge.svg?token=byliXGGyGB
+   :target: https://codecov.io/gh/iterative/datachain
    :alt: Codecov
-.. |Tests| image:: https://github.com/iterative/dvcx/workflows/Tests/badge.svg
-   :target: https://github.com/iterative/dvcx/actions?workflow=Tests
+.. |Tests| image:: https://github.com/iterative/datachain/workflows/Tests/badge.svg
+   :target: https://github.com/iterative/datachain/actions?workflow=Tests
    :alt: Tests
 
 AI 🔗 DataChain
@@ -397,7 +397,8 @@ Chain results can be exported or passed directly to Pytorch dataloader. For exam
 Tutorials
 ------------------
 
-* `Multimodal <examples/multimodal/clip_fine_tuning.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/dvclive/blob/main/examples/multimodal/clip_fine_tuning.ipynb>`__)
+* `Computer Vision <examples/computer_vision/fashion_product_images/1-quick-start.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain/blob/main/examples/computer_vision/fashion_product_images/1-quick-start.ipynb>`__)
+* `Multimodal <examples/multimodal/clip_fine_tuning.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain/blob/main/examples/multimodal/clip_fine_tuning.ipynb>`__)
 
 Contributions
 --------------------