datachain 0.6.1__tar.gz → 0.6.2__tar.gz

{datachain-0.6.1 → datachain-0.6.2}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.6.9'
+    rev: 'v0.7.0'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.6.1/src/datachain.egg-info → datachain-0.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.6.1
+Version: 0.6.2
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -19,8 +19,7 @@ License-File: LICENSE
 Requires-Dist: pyyaml
 Requires-Dist: tomlkit
 Requires-Dist: tqdm
-Requires-Dist: numpy
-Requires-Dist: numpy<2,>=1; sys_platform == "win32"
+Requires-Dist: numpy<3,>=1
 Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyarrow
 Requires-Dist: typing-extensions
@@ -39,11 +38,13 @@ Requires-Dist: orjson>=3.10.5
 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: Pillow<12,>=10.0.0
 Requires-Dist: msgpack<2,>=1.0.4
 Requires-Dist: psutil
 Requires-Dist: huggingface_hub
 Requires-Dist: iterative-telemetry>=0.0.9
+Requires-Dist: platformdirs
+Requires-Dist: dvc-studio-client<1,>=0.21
 Provides-Extra: docs
 Requires-Dist: mkdocs>=1.5.2; extra == "docs"
 Requires-Dist: mkdocs-gen-files>=0.5.0; extra == "docs"
@@ -81,7 +82,7 @@ Requires-Dist: requests-mock; extra == "tests"
 Requires-Dist: scipy; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
-Requires-Dist: mypy==1.12.0; extra == "dev"
+Requires-Dist: mypy==1.12.1; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
@@ -91,7 +92,7 @@ Requires-Dist: datachain[tests]; extra == "examples"
 Requires-Dist: numpy<2,>=1; extra == "examples"
 Requires-Dist: defusedxml; extra == "examples"
 Requires-Dist: accelerate; extra == "examples"
-Requires-Dist: unstructured[embed-huggingface,pdf]; extra == "examples"
+Requires-Dist: unstructured[embed-huggingface,pdf]<0.16.0; extra == "examples"
 Requires-Dist: pdfplumber==0.11.4; extra == "examples"
 Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
 Requires-Dist: onnx==1.16.1; extra == "examples"

{datachain-0.6.1 → datachain-0.6.2}/pyproject.toml

@@ -22,8 +22,7 @@ dependencies = [
   "pyyaml",
   "tomlkit",
   "tqdm",
-  "numpy",
-  'numpy>=1,<2; sys_platform == "win32"',
+  "numpy>=1,<3",
   "pandas>=2.0.0",
   "pyarrow",
   "typing-extensions",
@@ -42,11 +41,13 @@ dependencies = [
   "pydantic>=2,<3",
   "jmespath>=1.0",
   "datamodel-code-generator>=0.25",
-  "Pillow>=10.0.0,<11",
+  "Pillow>=10.0.0,<12",
   "msgpack>=1.0.4,<2",
   "psutil",
   "huggingface_hub",
-  "iterative-telemetry>=0.0.9"
+  "iterative-telemetry>=0.0.9",
+  "platformdirs",
+  "dvc-studio-client>=0.21,<1"
 ]
 
 [project.optional-dependencies]
@@ -93,7 +94,7 @@ tests = [
 ]
 dev = [
   "datachain[docs,tests]",
-  "mypy==1.12.0",
+  "mypy==1.12.1",
   "types-python-dateutil",
   "types-pytz",
   "types-PyYAML",
@@ -104,7 +105,7 @@ examples = [
   "numpy>=1,<2",
   "defusedxml",
   "accelerate",
-  "unstructured[pdf, embed-huggingface]",
+  "unstructured[pdf,embed-huggingface]<0.16.0",
   "pdfplumber==0.11.4",
   "huggingface_hub[hf_transfer]",
   "onnx==1.16.1"

{datachain-0.6.1 → datachain-0.6.2}/src/datachain/catalog/catalog.py

@@ -1,4 +1,3 @@
-import glob
 import io
 import json
 import logging
@@ -35,7 +34,6 @@ from tqdm import tqdm
 
 from datachain.cache import DataChainCache
 from datachain.client import Client
-from datachain.config import get_remote_config, read_config
 from datachain.dataset import (
     DATASET_PREFIX,
     QUERY_DATASET_PREFIX,
@@ -48,12 +46,10 @@ from datachain.dataset import (
     parse_dataset_uri,
 )
 from datachain.error import (
-    ClientError,
     DataChainError,
     DatasetInvalidVersionError,
     DatasetNotFoundError,
     DatasetVersionNotFoundError,
-    PendingIndexingError,
     QueryScriptCancelError,
     QueryScriptRunError,
 )
@@ -61,8 +57,8 @@ from datachain.listing import Listing
 from datachain.node import DirType, Node, NodeWithPath
 from datachain.nodes_thread_pool import NodesThreadPool
 from datachain.remote.studio import StudioClient
-from datachain.sql.types import JSON, Boolean, DateTime, Int64, SQLType, String
-from datachain.storage import Storage, StorageStatus, StorageURI
+from datachain.sql.types import DateTime, SQLType, String
+from datachain.storage import StorageURI
 from datachain.utils import (
     DataChainDir,
     batched,
@@ -102,7 +98,7 @@ PULL_DATASET_SLEEP_INTERVAL = 0.1  # sleep time while waiting for chunk to be av
 PULL_DATASET_CHECK_STATUS_INTERVAL = 20  # interval to check export status in Studio
 
 
-def _raise_remote_error(error_message: str) -> NoReturn:
+def raise_remote_error(error_message: str) -> NoReturn:
     raise DataChainError(f"Error from server: {error_message}")
 
 
@@ -130,7 +126,6 @@ class DatasetRowsFetcher(NodesThreadPool):
         self,
         metastore: "AbstractMetastore",
         warehouse: "AbstractWarehouse",
-        remote_config: dict[str, Any],
         dataset_name: str,
         dataset_version: int,
         schema: dict[str, Union[SQLType, type[SQLType]]],
@@ -144,10 +139,7 @@ class DatasetRowsFetcher(NodesThreadPool):
         self.dataset_version = dataset_version
         self.schema = schema
         self.last_status_check: Optional[float] = None
-
-        self.studio_client = StudioClient(
-            remote_config["url"], remote_config["username"], remote_config["token"]
-        )
+        self.studio_client = StudioClient()
 
     def done_task(self, done):
         for task in done:
@@ -181,14 +173,14 @@ class DatasetRowsFetcher(NodesThreadPool):
             self.dataset_name, self.dataset_version
         )
         if not export_status_response.ok:
-            _raise_remote_error(export_status_response.message)
+            raise_remote_error(export_status_response.message)
 
         export_status = export_status_response.data["status"]  # type: ignore [index]
 
         if export_status == "failed":
-            _raise_remote_error("Dataset export failed in Studio")
+            raise_remote_error("Dataset export failed in Studio")
         if export_status == "removed":
-            _raise_remote_error("Dataset export removed in Studio")
+            raise_remote_error("Dataset export removed in Studio")
 
         self.last_status_check = time.time()
 
@@ -483,17 +475,12 @@ def compute_metafile_data(node_groups) -> list[dict[str, Any]]:
         if not node_group.sources:
             continue
         listing: Listing = node_group.listing
-        source_path: str = node_group.source_path
-        if not node_group.is_dataset:
-            assert listing.storage
-            data_source = listing.storage.to_dict(source_path)
-        else:
-            data_source = {"uri": listing.metastore.uri}
-
-        metafile_group = {"data-source": data_source, "files": []}
+        metafile_group = {"data-source": {"uri": listing.uri}, "files": []}
         for node in node_group.instantiated_nodes:
             if not node.n.is_dir:
-                metafile_group["files"].append(node.get_metafile_data())
+                metafile_group["files"].append(  # type: ignore [attr-defined]
+                    node.get_metafile_data()
+                )
         if metafile_group["files"]:
             metafile_data.append(metafile_group)
 
@@ -569,6 +556,12 @@ class Catalog:
 
         return self._warehouse
 
+    @cached_property
+    def session(self):
+        from datachain.query.session import Session
+
+        return Session.get(catalog=self)
+
     def get_init_params(self) -> dict[str, Any]:
         return {
             **self._init_params,
@@ -599,162 +592,29 @@ class Catalog:
     def enlist_source(
         self,
         source: str,
-        ttl: int,
-        force_update=False,
-        skip_indexing=False,
+        update=False,
         client_config=None,
+        object_name="file",
+        skip_indexing=False,
     ) -> tuple[Listing, str]:
-        if force_update and skip_indexing:
-            raise ValueError(
-                "Both force_update and skip_indexing flags"
-                " cannot be True at the same time"
-            )
-
-        partial_id: Optional[int]
-        partial_path: Optional[str]
+        from datachain.lib.dc import DataChain
 
-        client_config = client_config or self.client_config
-        uri, path = Client.parse_url(source)
-        client = Client.get_client(source, self.cache, **client_config)
-        stem = os.path.basename(os.path.normpath(path))
-        prefix = (
-            posixpath.dirname(path)
-            if glob.has_magic(stem) or client.fs.isfile(source)
-            else path
+        DataChain.from_storage(
+            source, session=self.session, update=update, object_name=object_name
         )
-        storage_dataset_name = Storage.dataset_name(uri, posixpath.join(prefix, ""))
-        source_metastore = self.metastore.clone(uri)
-
-        columns = [
-            Column("path", String),
-            Column("etag", String),
-            Column("version", String),
-            Column("is_latest", Boolean),
-            Column("last_modified", DateTime(timezone=True)),
-            Column("size", Int64),
-            Column("location", JSON),
-            Column("source", String),
-        ]
-
-        if skip_indexing:
-            source_metastore.create_storage_if_not_registered(uri)
-            storage = source_metastore.get_storage(uri)
-            source_metastore.init_partial_id(uri)
-            partial_id = source_metastore.get_next_partial_id(uri)
-
-            source_metastore = self.metastore.clone(uri=uri, partial_id=partial_id)
-            source_metastore.init(uri)
-
-            source_warehouse = self.warehouse.clone()
-            dataset = self.create_dataset(
-                storage_dataset_name, columns=columns, listing=True
-            )
-
-            return (
-                Listing(storage, source_metastore, source_warehouse, client, dataset),
-                path,
-            )
-
-        (
-            storage,
-            need_index,
-            in_progress,
-            partial_id,
-            partial_path,
-        ) = source_metastore.register_storage_for_indexing(uri, force_update, prefix)
-        if in_progress:
-            raise PendingIndexingError(f"Pending indexing operation: uri={storage.uri}")
-
-        if not need_index:
-            assert partial_id is not None
-            assert partial_path is not None
-            source_metastore = self.metastore.clone(uri=uri, partial_id=partial_id)
-            source_warehouse = self.warehouse.clone()
-            dataset = self.get_dataset(Storage.dataset_name(uri, partial_path))
-            lst = Listing(storage, source_metastore, source_warehouse, client, dataset)
-            logger.debug(
-                "Using cached listing %s. Valid till: %s",
-                storage.uri,
-                storage.expires_to_local,
-            )
-            # Listing has to have correct version of data storage
-            # initialized with correct Storage
-
-            self.update_dataset_version_with_warehouse_info(
-                dataset,
-                dataset.latest_version,
-            )
-
-            return lst, path
 
-        source_metastore.init_partial_id(uri)
-        partial_id = source_metastore.get_next_partial_id(uri)
-
-        source_metastore.init(uri)
-        source_metastore = self.metastore.clone(uri=uri, partial_id=partial_id)
-
-        source_warehouse = self.warehouse.clone()
-
-        dataset = self.create_dataset(
-            storage_dataset_name, columns=columns, listing=True
+        list_ds_name, list_uri, list_path, _ = DataChain.parse_uri(
+            source, self.session, update=update
         )
 
-        lst = Listing(storage, source_metastore, source_warehouse, client, dataset)
-
-        try:
-            lst.fetch(prefix)
-
-            source_metastore.mark_storage_indexed(
-                storage.uri,
-                StorageStatus.PARTIAL if prefix else StorageStatus.COMPLETE,
-                ttl,
-                prefix=prefix,
-                partial_id=partial_id,
-                dataset=dataset,
-            )
-
-            self.update_dataset_version_with_warehouse_info(
-                dataset,
-                dataset.latest_version,
-            )
-
-        except ClientError as e:
-            # for handling cloud errors
-            error_message = INDEX_INTERNAL_ERROR_MESSAGE
-            if e.error_code in ["InvalidAccessKeyId", "SignatureDoesNotMatch"]:
-                error_message = "Invalid cloud credentials"
-
-            source_metastore.mark_storage_indexed(
-                storage.uri,
-                StorageStatus.FAILED,
-                ttl,
-                prefix=prefix,
-                error_message=error_message,
-                error_stack=traceback.format_exc(),
-                dataset=dataset,
-            )
-            self._remove_dataset_rows_and_warehouse_info(
-                dataset, dataset.latest_version
-            )
-            raise
-        except:
-            source_metastore.mark_storage_indexed(
-                storage.uri,
-                StorageStatus.FAILED,
-                ttl,
-                prefix=prefix,
-                error_message=INDEX_INTERNAL_ERROR_MESSAGE,
-                error_stack=traceback.format_exc(),
-                dataset=dataset,
-            )
-            self._remove_dataset_rows_and_warehouse_info(
-                dataset, dataset.latest_version
-            )
-            raise
-
-        lst.storage = storage
+        lst = Listing(
+            self.warehouse.clone(),
+            Client.get_client(list_uri, self.cache, **self.client_config),
+            self.get_dataset(list_ds_name),
+            object_name=object_name,
+        )
 
-        return lst, path
+        return lst, list_path
 
     def _remove_dataset_rows_and_warehouse_info(
         self, dataset: DatasetRecord, version: int, **kwargs
@@ -770,7 +630,6 @@ class Catalog:
     def enlist_sources(
         self,
         sources: list[str],
-        ttl: int,
         update: bool,
         skip_indexing=False,
         client_config=None,
@@ -780,10 +639,9 @@ class Catalog:
         for src in sources:  # Opt: parallel
             listing, file_path = self.enlist_source(
                 src,
-                ttl,
                 update,
-                skip_indexing=skip_indexing,
                 client_config=client_config or self.client_config,
+                skip_indexing=skip_indexing,
             )
             enlisted_sources.append((listing, file_path))
 
@@ -802,7 +660,6 @@ class Catalog:
     def enlist_sources_grouped(
         self,
         sources: list[str],
-        ttl: int,
         update: bool,
         no_glob: bool = False,
         client_config=None,
@@ -823,7 +680,6 @@ class Catalog:
                 for ds in edatachain_data:
                     listing, source_path = self.enlist_source(
                         ds["data-source"]["uri"],
-                        ttl,
                         update,
                         client_config=client_config,
                     )
@@ -843,11 +699,13 @@ class Catalog:
                 )
                 indexed_sources = []
                 for source in dataset_sources:
+                    from datachain.lib.dc import DataChain
+
                     client = self.get_client(source, **client_config)
                     uri = client.uri
-                    ms = self.metastore.clone(uri, None)
                     st = self.warehouse.clone()
-                    listing = Listing(None, ms, st, client, None)
+                    dataset_name, _, _, _ = DataChain.parse_uri(uri, self.session)
+                    listing = Listing(st, client, self.get_dataset(dataset_name))
                     rows = DatasetQuery(
                         name=dataset.name, version=ds_version, catalog=self
                     ).to_db_records()
@@ -864,7 +722,7 @@ class Catalog:
                 enlisted_sources.append((False, True, indexed_sources))
             else:
                 listing, source_path = self.enlist_source(
-                    src, ttl, update, client_config=client_config
+                    src, update, client_config=client_config
                 )
                 enlisted_sources.append((False, False, (listing, source_path)))
 
@@ -1115,19 +973,16 @@ class Catalog:
             raise ValueError("Sources needs to be non empty list")
 
         from datachain.lib.dc import DataChain
-        from datachain.query.session import Session
-
-        session = Session.get(catalog=self, client_config=client_config)
 
         chains = []
         for source in sources:
             if source.startswith(DATASET_PREFIX):
                 dc = DataChain.from_dataset(
-                    source[len(DATASET_PREFIX) :], session=session
+                    source[len(DATASET_PREFIX) :], session=self.session
                 )
             else:
                 dc = DataChain.from_storage(
-                    source, session=session, recursive=recursive
+                    source, session=self.session, recursive=recursive
                 )
 
             chains.append(dc)
@@ -1239,17 +1094,12 @@ class Catalog:
     def get_dataset(self, name: str) -> DatasetRecord:
         return self.metastore.get_dataset(name)
 
-    def get_remote_dataset(self, name: str, *, remote_config=None) -> DatasetRecord:
-        remote_config = remote_config or get_remote_config(
-            read_config(DataChainDir.find().root), remote=""
-        )
-        studio_client = StudioClient(
-            remote_config["url"], remote_config["username"], remote_config["token"]
-        )
+    def get_remote_dataset(self, name: str) -> DatasetRecord:
+        studio_client = StudioClient()
 
         info_response = studio_client.dataset_info(name)
         if not info_response.ok:
-            _raise_remote_error(info_response.message)
+            raise_remote_error(info_response.message)
 
         dataset_info = info_response.data
         assert isinstance(dataset_info, dict)
@@ -1306,6 +1156,20 @@ class Catalog:
                 for v in d.versions
             )
 
+    def listings(self):
+        """
+        Returns list of ListingInfo objects which are representing specific
+        storage listing datasets
+        """
+        from datachain.lib.listing import is_listing_dataset
+        from datachain.lib.listing_info import ListingInfo
+
+        return [
+            ListingInfo.from_models(d, v, j)
+            for d, v, j in self.list_datasets_versions(include_listing=True)
+            if is_listing_dataset(d.name)
+        ]
+
     def ls_dataset_rows(
         self, name: str, version: int, offset=None, limit=None
     ) -> list[dict]:
@@ -1430,7 +1294,6 @@ class Catalog:
         self,
         sources: list[str],
         fields: Iterable[str],
-        ttl=TTL_INT,
         update=False,
         skip_indexing=False,
         *,
@@ -1438,7 +1301,6 @@ class Catalog:
     ) -> Iterator[tuple[DataSource, Iterable[tuple]]]:
         data_sources = self.enlist_sources(
             sources,
-            ttl,
             update,
             skip_indexing=skip_indexing,
             client_config=client_config or self.client_config,
@@ -1457,7 +1319,6 @@ class Catalog:
         edatachain_file: Optional[str] = None,
         *,
         client_config=None,
-        remote_config=None,
     ) -> None:
         # TODO add progress bar https://github.com/iterative/dvcx/issues/750
         # TODO copy correct remote dates https://github.com/iterative/dvcx/issues/new
@@ -1479,13 +1340,8 @@ class Catalog:
             raise ValueError("Please provide output directory for instantiation")
 
         client_config = client_config or self.client_config
-        remote_config = remote_config or get_remote_config(
-            read_config(DataChainDir.find().root), remote=""
-        )
 
-        studio_client = StudioClient(
-            remote_config["url"], remote_config["username"], remote_config["token"]
-        )
+        studio_client = StudioClient()
 
         try:
             remote_dataset_name, version = parse_dataset_uri(dataset_uri)
@@ -1499,9 +1355,7 @@ class Catalog:
             # we will create new one if it doesn't exist
             pass
 
-        remote_dataset = self.get_remote_dataset(
-            remote_dataset_name, remote_config=remote_config
-        )
+        remote_dataset = self.get_remote_dataset(remote_dataset_name)
         # if version is not specified in uri, take the latest one
         if not version:
             version = remote_dataset.latest_version
@@ -1526,7 +1380,7 @@ class Catalog:
 
         stats_response = studio_client.dataset_stats(remote_dataset_name, version)
         if not stats_response.ok:
-            _raise_remote_error(stats_response.message)
+            raise_remote_error(stats_response.message)
         dataset_stats = stats_response.data
 
         dataset_save_progress_bar = tqdm(
@@ -1558,7 +1412,7 @@ class Catalog:
             remote_dataset_name, version
         )
         if not export_response.ok:
-            _raise_remote_error(export_response.message)
+            raise_remote_error(export_response.message)
 
         signed_urls = export_response.data
 
@@ -1572,7 +1426,6 @@ class Catalog:
                 rows_fetcher = DatasetRowsFetcher(
                     metastore,
                     warehouse,
-                    remote_config,
                     dataset.name,
                     version,
                     schema,
@@ -1615,7 +1468,6 @@ class Catalog:
         no_cp: bool = False,
         edatachain: bool = False,
         edatachain_file: Optional[str] = None,
-        ttl: int = TTL_INT,
         *,
         client_config=None,
     ) -> None:
@@ -1637,7 +1489,6 @@ class Catalog:
                 edatachain_only=no_cp,
                 no_edatachain_file=not edatachain,
                 edatachain_file=edatachain_file,
-                ttl=ttl,
                 client_config=client_config,
             )
         else:
@@ -1645,7 +1496,6 @@ class Catalog:
             # it needs to be done here
             self.enlist_sources(
                 sources,
-                ttl,
                 update,
                 client_config=client_config or self.client_config,
             )
@@ -1705,7 +1555,6 @@ class Catalog:
         edatachain_only: bool = False,
         no_edatachain_file: bool = False,
         no_glob: bool = False,
-        ttl: int = TTL_INT,
         *,
         client_config=None,
     ) -> list[dict[str, Any]]:
@@ -1717,7 +1566,6 @@ class Catalog:
         client_config = client_config or self.client_config
         node_groups = self.enlist_sources_grouped(
             sources,
-            ttl,
             update,
             no_glob,
             client_config=client_config,
@@ -1776,14 +1624,12 @@ class Catalog:
         self,
         sources,
         depth=0,
-        ttl=TTL_INT,
         update=False,
         *,
         client_config=None,
     ) -> Iterable[tuple[str, float]]:
         sources = self.enlist_sources(
             sources,
-            ttl,
             update,
             client_config=client_config or self.client_config,
         )
@@ -1804,7 +1650,6 @@ class Catalog:
     def find(
         self,
         sources,
-        ttl=TTL_INT,
         update=False,
         names=None,
         inames=None,
@@ -1818,7 +1663,6 @@ class Catalog:
     ) -> Iterator[str]:
         sources = self.enlist_sources(
             sources,
-            ttl,
             update,
             client_config=client_config or self.client_config,
         )
@@ -1854,7 +1698,6 @@ class Catalog:
     def index(
         self,
         sources,
-        ttl=TTL_INT,
         update=False,
         *,
         client_config=None,
@@ -1880,7 +1723,6 @@ class Catalog:
 
         self.enlist_sources(
             non_root_sources,
-            ttl,
             update,
             client_config=client_config,
             only_index=True,