datachain 0.31.0__tar.gz → 0.31.2__tar.gz

{datachain-0.31.0 → datachain-0.31.2}/.github/workflows/benchmarks.yml

@@ -20,7 +20,7 @@ jobs:
     steps:
       - uses: actions/checkout@v5
       - name: Set up Python 3.13
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.13'
 

{datachain-0.31.0 → datachain-0.31.2}/.github/workflows/release.yml

@@ -22,7 +22,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Python 3.13
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.13'
 

{datachain-0.31.0 → datachain-0.31.2}/.github/workflows/tests-studio.yml

@@ -92,7 +92,7 @@ jobs:
           sudo apt install -y ffmpeg
 
       - name: Set up Python ${{ matrix.pyv }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.pyv }}
 

{datachain-0.31.0 → datachain-0.31.2}/.github/workflows/tests.yml

@@ -24,7 +24,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.ref }}
 
       - name: Set up Python 3.9
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.9'
 
@@ -97,7 +97,7 @@ jobs:
         shell: bash
 
       - name: Set up Python ${{ matrix.pyv }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.pyv }}
 
@@ -114,9 +114,12 @@ jobs:
 
       - name: Install FFmpeg on macOS
         if: runner.os == 'macOS'
+        # Using ffmpeg@7 since torchcodec does not support ffmpeg 8 yet
+        # See: https://github.com/pytorch/torchcodec/issues/839
+        # On Windows and Linux ffmpeg < 8 is installed by default
         run: |
-          brew install ffmpeg
-          echo 'DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/lib' >> "$GITHUB_ENV"
+          brew install ffmpeg@7
+          echo 'DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/opt/ffmpeg@7/lib' >> "$GITHUB_ENV"
 
       - name: Install FFmpeg on Ubuntu
         if: runner.os == 'Linux'
@@ -180,7 +183,7 @@ jobs:
           ref: ${{ github.event.pull_request.head.sha || github.ref }}
 
       - name: Set up Python ${{ matrix.pyv }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.pyv }}
 

{datachain-0.31.0 → datachain-0.31.2}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.12.11'
+    rev: 'v0.12.12'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.31.0 → datachain-0.31.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.31.0
+Version: 0.31.2
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/client/fsspec.py

@@ -44,6 +44,7 @@ FETCH_WORKERS = 100
 DELIMITER = "/"  # Path delimiter.
 
 DATA_SOURCE_URI_PATTERN = re.compile(r"^[\w]+:\/\/.*$")
+CLOUD_STORAGE_PROTOCOLS = {"s3", "gs", "az", "hf"}
 
 ResultQueue = asyncio.Queue[Optional[Sequence["File"]]]
 
@@ -62,6 +63,16 @@ def _is_win_local_path(uri: str) -> bool:
     return False
 
 
+def is_cloud_uri(uri: str) -> bool:
+    protocol = urlparse(uri).scheme
+    return protocol in CLOUD_STORAGE_PROTOCOLS
+
+
+def get_cloud_schemes() -> list[str]:
+    """Get list of cloud storage scheme prefixes."""
+    return [f"{p}://" for p in CLOUD_STORAGE_PROTOCOLS]
+
+
 class Bucket(NamedTuple):
     name: str
     uri: "StorageURI"

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/clip.py

@@ -45,15 +45,15 @@ def clip_similarity_scores(
     Calculate CLIP similarity scores between one or more images and/or text.
 
     Parameters:
-        images : Images to use as inputs.
-        text : Text to use as inputs.
-        model : Model from clip or open_clip packages.
-        preprocess : Image preprocessor to apply.
-        tokenizer : Text tokenizer.
-        prob : Compute softmax probabilities.
-        image_to_text : Whether to compute for image-to-text or text-to-image. Ignored
-            if only one of images or text provided.
-        device : Device to use. Defaults is None - use model's device.
+        images: Images to use as inputs.
+        text: Text to use as inputs.
+        model: Model from clip or open_clip packages.
+        preprocess: Image preprocessor to apply.
+        tokenizer: Text tokenizer.
+        prob: Compute softmax probabilities.
+        image_to_text: Whether to compute for image-to-text or text-to-image. Ignored
+            if only one of the images or text provided.
+        device: Device to use. Default is None - use model's device.
 
 
     Example:

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/csv.py

@@ -1,10 +1,6 @@
+import os
 from collections.abc import Sequence
-from typing import (
-    TYPE_CHECKING,
-    Callable,
-    Optional,
-    Union,
-)
+from typing import TYPE_CHECKING, Callable, Optional, Union
 
 from datachain.lib.dc.utils import DatasetPrepareError, OutputType
 from datachain.lib.model_store import ModelStore
@@ -17,14 +13,14 @@ if TYPE_CHECKING:
 
 
 def read_csv(
-    path,
+    path: Union[str, os.PathLike[str], list[str], list[os.PathLike[str]]],
     delimiter: Optional[str] = None,
     header: bool = True,
     output: OutputType = None,
     column: str = "",
     model_name: str = "",
     source: bool = True,
-    nrows=None,
+    nrows: Optional[int] = None,
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
     column_types: Optional[dict[str, "Union[str, ArrowDataType]"]] = None,
@@ -34,21 +30,21 @@ def read_csv(
     """Generate chain from csv files.
 
     Parameters:
-        path : Storage URI with directory. URI must start with storage prefix such
+        path: Storage URI with directory. URI must start with storage prefix such
             as `s3://`, `gs://`, `az://` or "file:///".
-        delimiter : Character for delimiting columns. Takes precedence if also
+        delimiter: Character for delimiting columns. Takes precedence if also
             specified in `parse_options`. Defaults to ",".
-        header : Whether the files include a header row.
-        output : Dictionary or feature class defining column names and their
+        header: Whether the files include a header row.
+        output: Dictionary or feature class defining column names and their
             corresponding types. List of column names is also accepted, in which
             case types will be inferred.
-        column : Created column name.
-        model_name : Generated model name.
-        source : Whether to include info about the source file.
-        nrows : Optional row limit.
-        session : Session to use for the chain.
-        settings : Settings to use for the chain.
-        column_types : Dictionary of column names and their corresponding types.
+        column: Created column name.
+        model_name: Generated model name.
+        source: Whether to include info about the source file.
+        nrows: Optional row limit.
+        session: Session to use for the chain.
+        settings: Settings to use for the chain.
+        column_types: Dictionary of column names and their corresponding types.
             It is passed to CSV reader and for each column specified type auto
             inference is disabled.
         parse_options: Tells the parser how to process lines.

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/datachain.py

@@ -40,11 +40,7 @@ from datachain.lib.data_model import (
     StandardType,
     dict_to_data_model,
 )
-from datachain.lib.file import (
-    EXPORT_FILES_MAX_THREADS,
-    ArrowRow,
-    FileExporter,
-)
+from datachain.lib.file import EXPORT_FILES_MAX_THREADS, ArrowRow, FileExporter
 from datachain.lib.file import ExportPlacement as FileExportPlacement
 from datachain.lib.model_store import ModelStore
 from datachain.lib.settings import Settings
@@ -352,24 +348,28 @@ class DataChain:
         batch_size: Optional[int] = None,
         sys: Optional[bool] = None,
     ) -> "Self":
-        """Change settings for chain.
-
-        This function changes specified settings without changing not specified ones.
-        It returns chain, so, it can be chained later with next operation.
+        """
+        Set chain execution parameters. Returns the chain itself, allowing method
+        chaining for subsequent operations. To restore all settings to their default
+        values, use `reset_settings()`.
 
         Parameters:
-            cache : data caching. (default=False)
-            prefetch : number of workers to use for downloading files in advance.
-                      This is enabled by default and uses 2 workers.
-                      To disable prefetching, set it to 0 or False.
-            parallel : number of thread for processors. True is a special value to
-                enable all available CPUs. (default=1)
-            workers : number of distributed workers. Only for Studio mode. (default=1)
-            namespace : namespace name.
-            project : project name.
-            min_task_size : minimum number of tasks. (default=1)
-            batch_size : row limit per insert to balance speed and memory usage.
-                      (default=2000)
+            cache: Enable files caching to speed up subsequent accesses to the same
+                files from the same or different chains. Defaults to False.
+            prefetch: Enable prefetching of files. This will download files in
+                advance in parallel. If an integer is provided, it specifies the number
+                of files to prefetch concurrently for each process on each worker.
+                Defaults to 2. Set to 0 or False to disable prefetching.
+            parallel: Number of processes to use for processing user-defined functions
+                (UDFs) in parallel. If an integer is provided, it specifies the number
+                of CPUs to use. If True, all available CPUs are used. Defaults to 1.
+            namespace: Namespace to use for the chain by default.
+            project: Project to use for the chain by default.
+            min_task_size: Minimum number of rows per worker/process for parallel
+                processing by UDFs. Defaults to 1.
+            batch_size: Number of rows per insert by UDF to fine tune and balance speed
+                and memory usage. This might be useful when processing large rows
+                or when running into memory issues. Defaults to 2000.
 
         Example:
             ```py
@@ -398,7 +398,7 @@ class DataChain:
         return self._evolve(settings=settings, _sys=sys)
 
     def reset_settings(self, settings: Optional[Settings] = None) -> "Self":
-        """Reset all settings to default values."""
+        """Reset all chain settings to default values."""
         self._settings = settings if settings else Settings()
         return self
 
@@ -580,14 +580,14 @@ class DataChain:
         """Save to a Dataset. It returns the chain itself.
 
         Parameters:
-            name : dataset name. It can be full name consisting of namespace and
-                project, but it can also be just a regular dataset name in which
-                case we are taking namespace and project from settings, if they
-                are defined there, or default ones instead.
-            version : version of a dataset. If version is not specified and dataset
+            name: dataset name. This can be either a fully qualified name, including
+                the namespace and project, or just a regular dataset name. In the latter
+                case, the namespace and project will be taken from the settings
+                (if specified) or from the default values otherwise.
+            version: version of a dataset. If version is not specified and dataset
                 already exists, version patch increment will happen e.g 1.2.1 -> 1.2.2.
-            description : description of a dataset.
-            attrs : attributes of a dataset. They can be without value, e.g "NLP",
+            description: description of a dataset.
+            attrs: attributes of a dataset. They can be without value, e.g "NLP",
                 or with a value, e.g "location=US".
             update_version: which part of the dataset version to automatically increase.
                 Available values: `major`, `minor` or `patch`. Default is `patch`.
@@ -661,7 +661,9 @@ class DataChain:
                 # current latest version instead.
                 from .datasets import read_dataset
 
-                return read_dataset(name, **kwargs)
+                return read_dataset(
+                    name, namespace=namespace_name, project=project_name, **kwargs
+                )
 
         return self._evolve(
             query=self._query.save(
@@ -704,7 +706,7 @@ class DataChain:
         func: Optional[Callable] = None,
         params: Union[None, str, Sequence[str]] = None,
         output: OutputType = None,
-        **signal_map,
+        **signal_map: Any,
     ) -> "Self":
         """Apply a function to each row to create new signals. The function should
         return a new object for each row. It returns a chain itself with new signals.
@@ -712,17 +714,17 @@ class DataChain:
         Input-output relationship: 1:1
 
         Parameters:
-            func : Function applied to each row.
-            params : List of column names used as input for the function. Default
+            func: Function applied to each row.
+            params: List of column names used as input for the function. Default
                     is taken from function signature.
-            output : Dictionary defining new signals and their corresponding types.
+            output: Dictionary defining new signals and their corresponding types.
                     Default type is taken from function signature. Default can be also
                     taken from kwargs - **signal_map (see below).
                     If signal name is defined using signal_map (see below) only a single
                     type value can be used.
-            **signal_map : kwargs can be used to define `func` together with it's return
+            **signal_map: kwargs can be used to define `func` together with its return
                     signal name in format of `map(my_sign=my_func)`. This helps define
-                    signal names and function in a nicer way.
+                    signal names and functions in a nicer way.
 
         Example:
             Using signal_map and single type in output:
@@ -941,7 +943,7 @@ class DataChain:
         It accepts the same parameters plus an
         additional parameter:
 
-            batch : Size of each batch passed to `func`. Defaults to 1000.
+            batch: Size of each batch passed to `func`. Defaults to 1000.
 
         Example:
             ```py
@@ -1309,9 +1311,9 @@ class DataChain:
         """Yields flattened rows of values as a tuple.
 
         Args:
-            row_factory : A callable to convert row to a custom format.
-                          It should accept two arguments: a list of column names and
-                          a tuple of row values.
+            row_factory: A callable to convert row to a custom format.
+                It should accept two arguments: a list of column names and
+                a tuple of row values.
             include_hidden: Whether to include hidden signals from the schema.
         """
         db_signals = self._effective_signals_schema.db_signals(
@@ -1956,19 +1958,19 @@ class DataChain:
         model_name: str = "",
         source: bool = True,
         nrows: Optional[int] = None,
-        **kwargs,
+        **kwargs: Any,
     ) -> "Self":
         """Generate chain from list of tabular files.
 
         Parameters:
-            output : Dictionary or feature class defining column names and their
+            output: Dictionary or feature class defining column names and their
                 corresponding types. List of column names is also accepted, in which
                 case types will be inferred.
-            column : Generated column name.
-            model_name : Generated model name.
-            source : Whether to include info about the source file.
-            nrows : Optional row limit.
-            kwargs : Parameters to pass to pyarrow.dataset.dataset.
+            column: Generated column name.
+            model_name: Generated model name.
+            source: Whether to include info about the source file.
+            nrows: Optional row limit.
+            kwargs: Parameters to pass to pyarrow.dataset.dataset.
 
         Example:
             Reading a json lines file:
@@ -2098,12 +2100,12 @@ class DataChain:
         """Save chain to parquet file with SignalSchema metadata.
 
         Parameters:
-            path : Path or a file-like binary object to save the file. This supports
+            path: Path or a file-like binary object to save the file. This supports
                 local paths as well as remote paths, such as s3:// or hf:// with fsspec.
-            partition_cols : Column names by which to partition the dataset.
-            chunk_size : The chunk size of results to read and convert to columnar
+            partition_cols: Column names by which to partition the dataset.
+            chunk_size: The chunk size of results to read and convert to columnar
                 data, to avoid running out of memory.
-            fs_kwargs : Optional kwargs to pass to the fsspec filesystem, used only for
+            fs_kwargs: Optional kwargs to pass to the fsspec filesystem, used only for
                 write, for fsspec-type URLs, such as s3:// or hf:// when
                 provided as the destination path.
         """
@@ -2195,10 +2197,10 @@ class DataChain:
         """Save chain to a csv (comma-separated values) file.
 
         Parameters:
-            path : Path to save the file. This supports local paths as well as
+            path: Path to save the file. This supports local paths as well as
                 remote paths, such as s3:// or hf:// with fsspec.
-            delimiter : Delimiter to use for the resulting file.
-            fs_kwargs : Optional kwargs to pass to the fsspec filesystem, used only for
+            delimiter: Delimiter to use for the resulting file.
+            fs_kwargs: Optional kwargs to pass to the fsspec filesystem, used only for
                 write, for fsspec-type URLs, such as s3:// or hf:// when
                 provided as the destination path.
         """
@@ -2241,12 +2243,12 @@ class DataChain:
         """Save chain to a JSON file.
 
         Parameters:
-            path : Path to save the file. This supports local paths as well as
+            path: Path to save the file. This supports local paths as well as
                 remote paths, such as s3:// or hf:// with fsspec.
-            fs_kwargs : Optional kwargs to pass to the fsspec filesystem, used only for
+            fs_kwargs: Optional kwargs to pass to the fsspec filesystem, used only for
                 write, for fsspec-type URLs, such as s3:// or hf:// when
                 provided as the destination path.
-            include_outer_list : Sets whether to include an outer list for all rows.
+            include_outer_list: Sets whether to include an outer list for all rows.
                 Setting this to True makes the file valid JSON, while False instead
                 writes in the JSON lines format.
         """
@@ -2301,9 +2303,9 @@ class DataChain:
         """Save chain to a JSON lines file.
 
         Parameters:
-            path : Path to save the file. This supports local paths as well as
+            path: Path to save the file. This supports local paths as well as
                 remote paths, such as s3:// or hf:// with fsspec.
-            fs_kwargs : Optional kwargs to pass to the fsspec filesystem, used only for
+            fs_kwargs: Optional kwargs to pass to the fsspec filesystem, used only for
                 write, for fsspec-type URLs, such as s3:// or hf:// when
                 provided as the destination path.
         """
@@ -2571,9 +2573,9 @@ class DataChain:
                 The possible values are: "filename", "etag", "fullpath", and "checksum".
             link_type: Method to use for exporting files.
                 Falls back to `'copy'` if symlinking fails.
-            num_threads : number of threads to use for exporting files.
-                By default it uses 5 threads.
-            anon: If True, we will treat cloud bucket as public one. Default behavior
+            num_threads: number of threads to use for exporting files.
+                By default, it uses 5 threads.
+            anon: If True, we will treat cloud bucket as a public one. Default behavior
                 depends on the previous session configuration (e.g. happens in the
                 initial `read_storage`) and particular cloud storage client
                 implementation (e.g. S3 fallbacks to anonymous access if no credentials

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/datasets.py

@@ -51,14 +51,14 @@ def read_dataset(
             namespace and project. Alternatively, it can be a regular name, in which
             case the explicitly defined namespace and project will be used if they are
             set; otherwise, default values will be applied.
-        namespace : optional name of namespace in which dataset to read is created
-        project : optional name of project in which dataset to read is created
-        version : dataset version. Supports:
+        namespace: optional name of namespace in which dataset to read is created
+        project: optional name of project in which dataset to read is created
+        version: dataset version. Supports:
             - Exact version strings: "1.2.3"
             - Legacy integer versions: 1, 2, 3 (finds latest major version)
             - Version specifiers (PEP 440): ">=1.0.0,<2.0.0", "~=1.4.2", "==1.2.*", etc.
-        session : Session to use for the chain.
-        settings : Settings to use for the chain.
+        session: Session to use for the chain.
+        settings: Settings to use for the chain.
         delta: If True, only process new or changed files instead of reprocessing
             everything. This saves time by skipping files that were already processed in
             previous versions. The optimization is working when a new version of the
@@ -314,9 +314,9 @@ def delete_dataset(
             namespace and project. Alternatively, it can be a regular name, in which
             case the explicitly defined namespace and project will be used if they are
             set; otherwise, default values will be applied.
-        namespace : optional name of namespace in which dataset to delete is created
-        project : optional name of project in which dataset to delete is created
-        version : Optional dataset version
+        namespace: optional name of namespace in which dataset to delete is created
+        project: optional name of project in which dataset to delete is created
+        version: Optional dataset version
         force: If true, all datasets versions will be removed. Defaults to False.
         studio: If True, removes dataset from Studio only, otherwise removes local
             dataset. Defaults to False.

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/hf.py

@@ -1,8 +1,4 @@
-from typing import (
-    TYPE_CHECKING,
-    Optional,
-    Union,
-)
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from datachain.lib.data_model import dict_to_data_model
 from datachain.query import Session
@@ -20,28 +16,28 @@ if TYPE_CHECKING:
 
 def read_hf(
     dataset: Union[str, "HFDatasetType"],
-    *args,
+    *args: Any,
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
     column: str = "",
     model_name: str = "",
     limit: int = 0,
-    **kwargs,
+    **kwargs: Any,
 ) -> "DataChain":
     """Generate chain from Hugging Face Hub dataset.
 
     Parameters:
-        dataset : Path or name of the dataset to read from Hugging Face Hub,
+        dataset: Path or name of the dataset to read from Hugging Face Hub,
             or an instance of `datasets.Dataset`-like object.
-        args : Additional positional arguments to pass to `datasets.load_dataset`.
-        session : Session to use for the chain.
-        settings : Settings to use for the chain.
-        column : Generated object column name.
-        model_name : Generated model name.
-        limit : Limit the number of items to read from the HF dataset.
-                Adds `take(limit)` to the `datasets.load_dataset`.
-                Defaults to 0 (no limit).
-        kwargs : Parameters to pass to `datasets.load_dataset`.
+        args: Additional positional arguments to pass to `datasets.load_dataset`.
+        session: Session to use for the chain.
+        settings: Settings to use for the chain.
+        column: Generated object column name.
+        model_name: Generated model name.
+        limit: The maximum number of items to read from the HF dataset.
+            Applies `take(limit)` to `datasets.load_dataset`.
+            Defaults to 0 (no limit).
+        kwargs: Parameters to pass to `datasets.load_dataset`.
 
     Example:
         Load from Hugging Face Hub:

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/json.py

@@ -26,22 +26,22 @@ def read_json(
     column: Optional[str] = "",
     model_name: Optional[str] = None,
     format: Optional[str] = "json",
-    nrows=None,
+    nrows: Optional[int] = None,
     **kwargs,
 ) -> "DataChain":
     """Get data from JSON. It returns the chain itself.
 
     Parameters:
-        path : storage URI with directory. URI must start with storage prefix such
+        path: storage URI with directory. URI must start with storage prefix such
             as `s3://`, `gs://`, `az://` or "file:///"
-        type : read file as "binary", "text", or "image" data. Default is "text".
-        spec : optional Data Model
-        schema_from : path to sample to infer spec (if schema not provided)
-        column : generated column name
-        model_name : optional generated model name
+        type: read file as "binary", "text", or "image" data. Default is "text".
+        spec: optional Data Model
+        schema_from: path to sample to infer spec (if schema not provided)
+        column: generated column name
+        model_name: optional generated model name
         format: "json", "jsonl"
-        jmespath : optional JMESPATH expression to reduce JSON
-        nrows : optional row limit for jsonl and JSON arrays
+        jmespath: optional JMESPATH expression to reduce JSON
+        nrows: optional row limit for jsonl and JSON arrays
 
     Example:
         infer JSON schema from data, reduce using JMESPATH

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/parquet.py

@@ -1,8 +1,5 @@
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Optional,
-)
+import os
+from typing import TYPE_CHECKING, Any, Optional, Union
 
 from datachain.lib.data_model import DataType
 from datachain.query import Session
@@ -16,7 +13,7 @@ if TYPE_CHECKING:
 
 
 def read_parquet(
-    path,
+    path: Union[str, os.PathLike[str], list[str], list[os.PathLike[str]]],
     partitioning: Any = "hive",
     output: Optional[dict[str, DataType]] = None,
     column: str = "",
@@ -29,15 +26,15 @@ def read_parquet(
     """Generate chain from parquet files.
 
     Parameters:
-        path : Storage URI with directory. URI must start with storage prefix such
+        path: Storage URI with directory. URI must start with storage prefix such
             as `s3://`, `gs://`, `az://` or "file:///".
-        partitioning : Any pyarrow partitioning schema.
-        output : Dictionary defining column names and their corresponding types.
-        column : Created column name.
-        model_name : Generated model name.
-        source : Whether to include info about the source file.
-        session : Session to use for the chain.
-        settings : Settings to use for the chain.
+        partitioning: Any pyarrow partitioning schema.
+        output: Dictionary defining column names and their corresponding types.
+        column: Created column name.
+        model_name: Generated model name.
+        source: Whether to include info about the source file.
+        session: Session to use for the chain.
+        settings: Settings to use for the chain.
 
     Example:
         Reading a single file:

{datachain-0.31.0 → datachain-0.31.2}/src/datachain/lib/dc/records.py

@@ -30,9 +30,9 @@ def read_records(
     or other sources.
 
     Parameters:
-        to_insert : records (or a single record) to insert. Each record is
+        to_insert: records (or a single record) to insert. Each record is
                     a dictionary of signals and their values.
-        schema : describes chain signals and their corresponding types
+        schema: describes chain signals and their corresponding types
 
     Example:
         ```py