datachain 0.6.8__py3-none-any.whl → 0.6.9__py3-none-any.whl

datachain/catalog/catalog.py

@@ -769,6 +769,7 @@ class Catalog:
         create_rows: Optional[bool] = True,
         validate_version: Optional[bool] = True,
         listing: Optional[bool] = False,
+        uuid: Optional[str] = None,
     ) -> "DatasetRecord":
         """
         Creates new dataset of a specific version.
@@ -816,6 +817,7 @@ class Catalog:
             query_script=query_script,
             create_rows_table=create_rows,
             columns=columns,
+            uuid=uuid,
         )
 
     def create_new_dataset_version(
@@ -832,6 +834,7 @@ class Catalog:
         script_output="",
         create_rows_table=True,
         job_id: Optional[str] = None,
+        uuid: Optional[str] = None,
     ) -> DatasetRecord:
         """
         Creates dataset version if it doesn't exist.
@@ -855,6 +858,7 @@ class Catalog:
             schema=schema,
             job_id=job_id,
             ignore_if_exists=True,
+            uuid=uuid,
         )
 
         if create_rows_table:
@@ -1400,6 +1404,7 @@ class Catalog:
             columns=columns,
             feature_schema=remote_dataset_version.feature_schema,
             validate_version=False,
+            uuid=remote_dataset_version.uuid,
         )
 
         # asking remote to export dataset rows table to s3 and to return signed

datachain/client/fsspec.py

@@ -358,7 +358,7 @@ class Client(ABC):
     ) -> BinaryIO:
         """Open a file, including files in tar archives."""
         if use_cache and (cache_path := self.cache.get_path(file)):
-            return open(cache_path, mode="rb")  # noqa: SIM115
+            return open(cache_path, mode="rb")
         assert not file.location
         return FileWrapper(self.fs.open(self.get_full_path(file.path)), cb)  # type: ignore[return-value]
 

datachain/data_storage/metastore.py

@@ -138,6 +138,7 @@ class AbstractMetastore(ABC, Serializable):
         size: Optional[int] = None,
         preview: Optional[list[dict]] = None,
         job_id: Optional[str] = None,
+        uuid: Optional[str] = None,
     ) -> DatasetRecord:
         """Creates new dataset version."""
 
@@ -352,6 +353,7 @@ class AbstractDBMetastore(AbstractMetastore):
         """Datasets versions table columns."""
         return [
             Column("id", Integer, primary_key=True),
+            Column("uuid", Text, nullable=False, default=uuid4()),
             Column(
                 "dataset_id",
                 Integer,
@@ -545,6 +547,7 @@ class AbstractDBMetastore(AbstractMetastore):
         size: Optional[int] = None,
         preview: Optional[list[dict]] = None,
         job_id: Optional[str] = None,
+        uuid: Optional[str] = None,
         conn=None,
     ) -> DatasetRecord:
         """Creates new dataset version."""
@@ -555,6 +558,7 @@ class AbstractDBMetastore(AbstractMetastore):
 
         query = self._datasets_versions_insert().values(
             dataset_id=dataset.id,
+            uuid=uuid or str(uuid4()),
             version=version,
             status=status,
             feature_schema=json.dumps(feature_schema or {}),

datachain/dataset.py

@@ -163,6 +163,7 @@ class DatasetStatus:
 @dataclass
 class DatasetVersion:
     id: int
+    uuid: str
     dataset_id: int
     version: int
     status: int
@@ -184,6 +185,7 @@ class DatasetVersion:
     def parse(  # noqa: PLR0913
         cls: type[V],
         id: int,
+        uuid: str,
         dataset_id: int,
         version: int,
         status: int,
@@ -203,6 +205,7 @@ class DatasetVersion:
     ):
         return cls(
             id,
+            uuid,
             dataset_id,
             version,
             status,
@@ -306,6 +309,7 @@ class DatasetRecord:
         query_script: str,
         schema: str,
         version_id: int,
+        version_uuid: str,
         version_dataset_id: int,
         version: int,
         version_status: int,
@@ -331,6 +335,7 @@ class DatasetRecord:
 
         dataset_version = DatasetVersion.parse(
             version_id,
+            version_uuid,
             version_dataset_id,
             version,
             version_status,

datachain/lib/dataset_info.py

@@ -1,6 +1,7 @@
 import json
 from datetime import datetime
 from typing import TYPE_CHECKING, Any, Optional, Union
+from uuid import uuid4
 
 from pydantic import Field, field_validator
 
@@ -15,6 +16,7 @@ if TYPE_CHECKING:
 
 class DatasetInfo(DataModel):
     name: str
+    uuid: str = Field(default=str(uuid4()))
     version: int = Field(default=1)
     status: int = Field(default=DatasetStatus.CREATED)
     created_at: datetime = Field(default=TIME_ZERO)
@@ -60,6 +62,7 @@ class DatasetInfo(DataModel):
         job: Optional[Job],
     ) -> "Self":
         return cls(
+            uuid=version.uuid,
             name=dataset.name,
             version=version.version,
             status=version.status,

datachain/lib/dc.py

@@ -30,7 +30,7 @@ from datachain.client.local import FileClient
 from datachain.dataset import DatasetRecord
 from datachain.lib.convert.python_to_sql import python_to_sql
 from datachain.lib.convert.values_to_tuples import values_to_tuples
-from datachain.lib.data_model import DataModel, DataType, dict_to_data_model
+from datachain.lib.data_model import DataModel, DataType, DataValue, dict_to_data_model
 from datachain.lib.dataset_info import DatasetInfo
 from datachain.lib.file import ArrowRow, File, get_file_type
 from datachain.lib.file import ExportPlacement as FileExportPlacement
@@ -895,7 +895,7 @@ class DataChain:
         2. Group-based UDF function input: Instead of individual rows, the function
            receives a list all rows within each group defined by `partition_by`.
 
-        Example:
+        Examples:
             ```py
             chain = chain.agg(
                 total=lambda category, amount: [sum(amount)],
@@ -904,6 +904,26 @@ class DataChain:
             )
             chain.save("new_dataset")
             ```
+
+            An alternative syntax, when you need to specify a more complex function:
+
+            ```py
+            # It automatically resolves which columns to pass to the function
+            # by looking at the function signature.
+            def agg_sum(
+                file: list[File], amount: list[float]
+            ) -> Iterator[tuple[File, float]]:
+                yield file[0], sum(amount)
+
+            chain = chain.agg(
+                agg_sum,
+                output={"file": File, "total": float},
+                # Alternative syntax is to use `C` (short for Column) to specify
+                # a column name or a nested column, e.g. C("file.path").
+                partition_by=C("category"),
+            )
+            chain.save("new_dataset")
+            ```
         """
         udf_obj = self._udf_to_obj(Aggregator, func, params, output, signal_map)
         return self._evolve(
@@ -1242,15 +1262,15 @@ class DataChain:
         return self.results(row_factory=to_dict)
 
     @overload
-    def collect(self) -> Iterator[tuple[DataType, ...]]: ...
+    def collect(self) -> Iterator[tuple[DataValue, ...]]: ...
 
     @overload
-    def collect(self, col: str) -> Iterator[DataType]: ...  # type: ignore[overload-overlap]
+    def collect(self, col: str) -> Iterator[DataValue]: ...
 
     @overload
-    def collect(self, *cols: str) -> Iterator[tuple[DataType, ...]]: ...
+    def collect(self, *cols: str) -> Iterator[tuple[DataValue, ...]]: ...
 
-    def collect(self, *cols: str) -> Iterator[Union[DataType, tuple[DataType, ...]]]:  # type: ignore[overload-overlap,misc]
+    def collect(self, *cols: str) -> Iterator[Union[DataValue, tuple[DataValue, ...]]]:  # type: ignore[overload-overlap,misc]
         """Yields rows of values, optionally limited to the specified columns.
 
         Args:

datachain/lib/meta_formats.py

@@ -114,6 +114,7 @@ def read_meta(  # noqa: C901
             )
         )
         (model_output,) = chain.collect("meta_schema")
+        assert isinstance(model_output, str)
         if print_schema:
             print(f"{model_output}")
         # Below 'spec' should be a dynamically converted DataModel from Pydantic

datachain/lib/signal_schema.py

@@ -378,7 +378,7 @@ class SignalSchema:
 
     def row_to_features(
         self, row: Sequence, catalog: "Catalog", cache: bool = False
-    ) -> list[DataType]:
+    ) -> list[DataValue]:
         res = []
         pos = 0
         for fr_cls in self.values.values():

{datachain-0.6.8.dist-info → datachain-0.6.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.8
+Version: 0.6.9
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -120,33 +120,41 @@ Requires-Dist: usearch ; extra == 'vector'
    :target: https://github.com/iterative/datachain/actions/workflows/tests.yml
    :alt: Tests
 
-DataChain is a modern Pythonic data-frame library designed for artificial intelligence.
-It is made to organize your unstructured data into datasets and wrangle it at scale on
-your local machine. Datachain does not abstract or hide the AI models and API calls, but helps to integrate them into the postmodern data stack.
+DataChain is a Python-based AI-data warehouse for transforming and analyzing unstructured
+data like images, audio, videos, text and PDFs. It integrates with external storage
+(e.g., S3) to process data efficiently without data duplication and manages metadata
+in an internal database for easy and efficient querying.
+
+
+Use Cases
+=========
+
+1. **Multimodal Dataset Preparation and Curation**: ideal for organizing and
+   refining data in pre-training, finetuning or LLM evaluating stages.
+2. **GenAI Data Analytics**: Enables advanced analytics for multimodal data and
+   ad-hoc analytics using LLMs.
 
 Key Features
 ============
 
-📂 **Storage as a Source of Truth.**
-   - Process unstructured data without redundant copies from S3, GCP, Azure, and local
-     file systems.
-   - Multimodal data support: images, video, text, PDFs, JSONs, CSVs, parquet.
+📂 **Multimodal Dataset Versioning.**
+   - Version unstructured data without redundant data copies, by supporitng
+     references to S3, GCP, Azure, and local file systems.
+   - Multimodal data support: images, video, text, PDFs, JSONs, CSVs, parquet, etc.
    - Unite files and metadata together into persistent, versioned, columnar datasets.
 
-🐍 **Python-friendly data pipelines.**
-   - Operate on Python objects and object fields.
-   - Built-in parallelization and out-of-memory compute without SQL or Spark.
+🐍 **Python-friendly.**
+   - Operate on Python objects and object fields: float scores, strings, matrixes,
+     LLM response objects.
+   - Run Python code in a high-scale, terabytes size datasets, with built-in
+     parallelization and memory-efficient computing — no SQL or Spark required.
 
 🧠 **Data Enrichment and Processing.**
    - Generate metadata using local AI models and LLM APIs.
-   - Filter, join, and group by metadata. Search by vector embeddings.
+   - Filter, join, and group datasets by metadata. Search by vector embeddings.
+   - High-performance vectorized operations on Python objects: sum, count, avg, etc.
    - Pass datasets to Pytorch and Tensorflow, or export them back into storage.
 
-🚀 **Efficiency.**
-   - Parallelization, out-of-memory workloads and data caching.
-   - Vectorized operations on Python object fields: sum, count, avg, etc.
-   - Optimized vector search.
-
 
 Quick Start
 -----------
@@ -196,7 +204,7 @@ Batch inference with a simple sentiment model using the `transformers` library:
 
     pip install transformers
 
-The code below downloads files the cloud, and applies a user-defined function
+The code below downloads files from the cloud, and applies a user-defined function
 to each one of them. All files with a positive sentiment
 detected are then copied to the local directory.
 
@@ -429,6 +437,19 @@ name suffix, the following code will do it:
     loader = DataLoader(chain, batch_size=1)
 
 
+DataChain Studio Platform
+-------------------------
+
+`DataChain Studio`_ is a proprietary solution for teams that offers:
+
+- **Centralized dataset registry** to manage data, code and dependency
+  dependencies in one place.
+- **Data Lineage** for data sources as well as direvative dataset.
+- **UI for Multimodal Data** like images, videos, and PDFs.
+- **Scalable Compute** to handle large datasets (100M+ files) and in-house
+  AI model inference.
+- **Access control** including SSO and team based collaboration.
+
 Tutorials
 ---------
 
@@ -462,6 +483,5 @@ Community and Support
 .. _Pydantic: https://github.com/pydantic/pydantic
 .. _publicly available: https://radar.kit.edu/radar/en/dataset/FdJmclKpjHzLfExE.ExpBot%2B-%2BA%2Bdataset%2Bof%2B79%2Bdialogs%2Bwith%2Ban%2Bexperimental%2Bcustomer%2Bservice%2Bchatbot
 .. _SQLite: https://www.sqlite.org/
-.. _Getting Started: https://datachain.dvc.ai/
-.. |Flowchart| image:: https://github.com/iterative/datachain/blob/main/docs/assets/flowchart.png?raw=true
-   :alt: DataChain FlowChart
+.. _Getting Started: https://docs.datachain.ai/
+.. _DataChain Studio: https://studio.datachain.ai/

{datachain-0.6.8.dist-info → datachain-0.6.9.dist-info}/RECORD

@@ -5,7 +5,7 @@ datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
 datachain/cli.py,sha256=hdVt_HJumQVgtaBAtBVJm-uPyYVogMXNVLmRcZyWHgk,36677
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
-datachain/dataset.py,sha256=lLUbUbJP1TYL9Obkc0f2IDziGcDylZge9ORQjK-WtXs,14717
+datachain/dataset.py,sha256=0IN-5y723y-bnFlieKtOFZLCjwX_yplFo3q0DV7LRPw,14821
 datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
 datachain/listing.py,sha256=AV23WZq-k6e2zeeNBhVQP1-2PrwNCYidO0HBDKzpVaA,7152
@@ -18,13 +18,13 @@ datachain/studio.py,sha256=6kxF7VxPAbh9D7_Bk8_SghS5OXrwUwSpDaw19eNCTP4,4083
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=-mSFowjIidJ4_sMXInvNHLn4rK_QnHuIlLuH1_lMGmI,13897
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=VwItaZG8MUqNKYz0xopDCdkVkbbxgTZYky3ElgsK5-M,57183
+datachain/catalog/catalog.py,sha256=Iwb562grttdGcrNVHCna_n7e884BqwGhQwAgYagBwyg,57347
 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
 datachain/client/azure.py,sha256=ffxs26zm6KLAL1aUWJm-vtzuZP3LSNha7UDGXynMBKo,2234
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
-datachain/client/fsspec.py,sha256=C6C5AO6ndkgcoUxCRN9_8fUzqX2cRWJWG6FL6oD9X_Q,12708
+datachain/client/fsspec.py,sha256=Ai5m7alkAnv-RWXuLbZ95SKEPaQ3Pyk5ujDy50JDX5w,12692
 datachain/client/gcs.py,sha256=cnTIr5GS6dbYOEYfqehhyQu3dr6XNjPHSg5U3FkivUk,4124
 datachain/client/hf.py,sha256=XeVJVbiNViZCpn3sfb90Fr8SYO3BdLmfE3hOWMoqInE,951
 datachain/client/local.py,sha256=vwbgCwZ7IqY2voj2l7tLJjgov7Dp--fEUvUwUBsMbls,4457
@@ -33,7 +33,7 @@ datachain/data_storage/__init__.py,sha256=cEOJpyu1JDZtfUupYucCDNFI6e5Wmp_Oyzq6rZ
 datachain/data_storage/db_engine.py,sha256=81Ol1of9TTTzD97ORajCnP366Xz2mEJt6C-kTUCaru4,3406
 datachain/data_storage/id_generator.py,sha256=lCEoU0BM37Ai2aRpSbwo5oQT0GqZnSpYwwvizathRMQ,4292
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
-datachain/data_storage/metastore.py,sha256=-TJCqG70VofSVOh2yEez4dwjHS3eQL8p7d9uO3WTVwM,35878
+datachain/data_storage/metastore.py,sha256=5b7o_CSHC2djottebYn-Hq5q0yaSLOKPIRCnaVRvjsU,36056
 datachain/data_storage/schema.py,sha256=scANMQqozita3HjEtq7eupMgh6yYkrZHoXtfuL2RoQg,9879
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
 datachain/data_storage/sqlite.py,sha256=wb8xlMJYYyt59wft0psJj587d-AwpNThzIqspVcKnRI,27388
@@ -42,18 +42,18 @@ datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/arrow.py,sha256=-hu9tic79a01SY2UBqkA3U6wUr6tnE3T3q5q_BnO93A,9156
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=dau4AlZBhOFvF7pEKMeqCeRkcFFg5KFvTBWW_2CdH5g,2371
-datachain/lib/dataset_info.py,sha256=srPPhI2UHf6hFPBecyFEVw2SS5aPisIIMsvGgKqi7ss,2366
-datachain/lib/dc.py,sha256=U1evAvSs563OMuUVildoaIOuOFiNB6fZcsN4BI8L9f0,85076
+datachain/lib/dataset_info.py,sha256=q0EW9tj5jXGSD9Lzct9zbH4P1lfIGd_cIWqhnMxv7Q0,2464
+datachain/lib/dc.py,sha256=RQ8p95rzCMRY4ygFecO_hhQ3IgQHmbLXNqhcaINvGcI,85841
 datachain/lib/file.py,sha256=lHxE1wOGR4QJBQ3AYjhPLwpX72dOi06vkcwA-WSAGlg,14817
 datachain/lib/hf.py,sha256=BW2NPpqxkpPwkSaGlppT8Rbs8zPpyYC-tR6htY08c-0,5817
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
 datachain/lib/listing.py,sha256=cVkCp7TRVpcZKSx-Bbk9t51bQI9Mw0o86W6ZPhAsuzM,3667
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
-datachain/lib/meta_formats.py,sha256=3f-0vpMTesagS9iMd3y9-u9r-7g0eqYsxmK4fVfNWlw,6635
+datachain/lib/meta_formats.py,sha256=anK2bDVbaeCCh0yvKUBaW2MVos3zRgdaSV8uSduzPcU,6680
 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=mQuviKAdZzFtZcbZHhqzUP-zivQ9MDZiLQhE54OPbOA,24555
+datachain/lib/signal_schema.py,sha256=xwkE5bxJxUhZTjrA6jqN87XbSXPikCbL6eOPL9WyrKM,24556
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
 datachain/lib/udf.py,sha256=4CqK51n3bntXCmkwoOQIrX34wMKOknkC23HtR4D_2vM,12705
@@ -104,9 +104,9 @@ datachain/sql/sqlite/base.py,sha256=aHSZVvh4XSVkvZ07h3jMoRlHI4sWD8y3SnmGs9xMG9Y,
 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-0.6.8.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.6.8.dist-info/METADATA,sha256=NDeFhQSQOSP3URzciSjDJnWyC9T3O8ptZmwOU8lDBSI,17259
-datachain-0.6.8.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-datachain-0.6.8.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.6.8.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.6.8.dist-info/RECORD,,
+datachain-0.6.9.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.6.9.dist-info/METADATA,sha256=McKhuW43_7Q3iJKxueIYbk-rpYF6rbIKeFinzeeUzMo,18037
+datachain-0.6.9.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+datachain-0.6.9.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.6.9.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.6.9.dist-info/RECORD,,

{datachain-0.6.8.dist-info → datachain-0.6.9.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (75.5.0)
 Root-Is-Purelib: true
 Tag: py3-none-any