nextmv 0.29.0.dev0__py3-none-any.whl → 0.29.2.dev1__py3-none-any.whl

nextmv/__about__.py

@@ -1 +1 @@
-__version__ = "v0.29.0.dev0"
+__version__ = "v0.29.2.dev1"

nextmv/cloud/application.py

@@ -1573,6 +1573,13 @@ class Application:
         json_configurations: Optional[dict[str, Any]]
             Optional configurations for JSON serialization. This is used to
             customize the serialization before data is sent.
+        dir_path: Optional[str]
+            Path to a directory containing input files. If specified, the
+            function will package the files in the directory into a tar file
+            and upload it as a large input. This is useful for input formats
+            like `nextmv.InputFormat.CSV_ARCHIVE` or `nextmv.InputFormat.MULTI_FILE`.
+            If both `input` and `dir_path` are specified, the `input` is
+            ignored, and the files in the directory are used instead.
 
         Returns
         ----------
@@ -1612,10 +1619,8 @@ class Application:
         if input_data is not None:
             input_size = get_size(input_data)
 
-        upload_url_required = input_size > _MAX_RUN_SIZE or tar_file != ""
         upload_id_used = upload_id is not None
-
-        if not upload_id_used and upload_url_required:
+        if self.__upload_url_required(upload_id_used, input_size, tar_file, input):
             upload_url = self.upload_url()
             self.upload_large_input(input=input_data, upload_url=upload_url, tar_file=tar_file)
             upload_id = upload_url.upload_id
@@ -1650,11 +1655,18 @@ class Application:
                 if not isinstance(v, str):
                     raise ValueError(f"options must be dict[str,str], option {k} has type {type(v)} instead.")
             payload["options"] = options_dict
+
         if configuration is not None:
             configuration_dict = (
                 configuration.to_dict() if isinstance(configuration, RunConfiguration) else configuration
             )
-            payload["configuration"] = configuration_dict
+        else:
+            configuration = RunConfiguration()
+            configuration.resolve(input=input, dir_path=dir_path)
+            configuration_dict = configuration.to_dict()
+
+        payload["configuration"] = configuration_dict
+
         if batch_experiment_id is not None:
             payload["batch_experiment_id"] = batch_experiment_id
         if external_result is not None:
@@ -1688,6 +1700,8 @@ class Application:
         configuration: Optional[Union[RunConfiguration, dict[str, Any]]] = None,
         batch_experiment_id: Optional[str] = None,
         external_result: Optional[Union[ExternalRunResult, dict[str, Any]]] = None,
+        json_configurations: Optional[dict[str, Any]] = None,
+        dir_path: Optional[str] = None,
     ) -> RunResult:
         """
         Submit an input to start a new run of the application and poll for the
@@ -1699,11 +1713,35 @@ class Application:
         ----------
         input: Union[Input, dict[str, Any], BaseModel, str]
             Input to use for the run. This can be a `nextmv.Input` object,
-            `dict`, `BaseModel` or `str`. If `nextmv.Input` is used, then the
-            input is extracted from the `.data` property. Note that for now,
-            `InputFormat.CSV_ARCHIVE` is not supported as an
-            `input.input_format`. If an input is too large, it will be uploaded
-            with the `upload_large_input` method.
+            `dict`, `BaseModel` or `str`.
+
+            If `nextmv.Input` is used, and the `input_format` is either
+            `nextmv.InputFormat.JSON` or `nextmv.InputFormat.TEXT`, then the
+            input data is extracted from the `.data` property.
+
+            If you want to work with `nextmv.InputFormat.CSV_ARCHIVE` or
+            `nextmv.InputFormat.MULTI_FILE`, you should use the `dir_path`
+            argument instead. This argument takes precedence over the `input`.
+            If `dir_path` is specified, this function looks for files in that
+            directory and tars them, to later be uploaded using the
+            `upload_large_input` method. If both the `dir_path` and `input`
+            arguments are provided, the `input` is ignored.
+
+            When `dir_path` is specified, the `configuration` argument must
+            also be provided. More specifically, the
+            `RunConfiguration.format.format_input.input_type` parameter
+            dictates what kind of input is being submitted to the Nextmv Cloud.
+            Make sure that this parameter is specified when working with the
+            following input formats:
+
+            - `nextmv.InputFormat.CSV_ARCHIVE`
+            - `nextmv.InputFormat.MULTI_FILE`
+
+            When working with JSON or text data, use the `input` argument
+            directly.
+
+            In general, if an input is too large, it will be uploaded with the
+            `upload_large_input` method.
         instance_id: Optional[str]
             ID of the instance to use for the run. If not provided, the default
             instance ID associated to the Class (`default_instance_id`) is
@@ -1743,6 +1781,16 @@ class Application:
             configuration. This is used when the run is an external run. We
             suggest that instead of specifying this parameter, you use the
             `track_run_with_result` method of the class.
+        json_configurations: Optional[dict[str, Any]]
+            Optional configurations for JSON serialization. This is used to
+            customize the serialization before data is sent.
+        dir_path: Optional[str]
+            Path to a directory containing input files. If specified, the
+            function will package the files in the directory into a tar file
+            and upload it as a large input. This is useful for input formats
+            like `nextmv.InputFormat.CSV_ARCHIVE` or `nextmv.InputFormat.MULTI_FILE`.
+            If both `input` and `dir_path` are specified, the `input` is
+            ignored, and the files in the directory are used instead.
 
         Returns
         ----------
@@ -1774,6 +1822,8 @@ class Application:
             configuration=configuration,
             batch_experiment_id=batch_experiment_id,
             external_result=external_result,
+            json_configurations=json_configurations,
+            dir_path=dir_path,
         )
 
         return self.run_result_with_polling(
@@ -3297,6 +3347,33 @@ class Application:
 
         return tar_file_path
 
+    def __upload_url_required(
+        self,
+        upload_id_used: bool,
+        input_size: int,
+        tar_file: str,
+        input: Union[Input, dict[str, Any], BaseModel, str] = None,
+    ) -> bool:
+        """
+        Auxiliary function to determine if an upload URL is required
+        based on the input size, type, and configuration.
+        """
+
+        if upload_id_used:
+            return False
+
+        non_json_payload = False
+        if isinstance(input, str):
+            non_json_payload = True
+        elif isinstance(input, Input) and input.input_format != InputFormat.JSON:
+            non_json_payload = True
+        elif tar_file is not None and tar_file != "":
+            non_json_payload = True
+
+        size_exceeds = input_size > _MAX_RUN_SIZE
+
+        return size_exceeds or non_json_payload
+
 
 def poll(  # noqa: C901
     polling_options: PollingOptions,

nextmv/cloud/client.py

@@ -397,7 +397,7 @@ class Client:
 
         if upload_data is not None:
             kwargs["data"] = upload_data
-        elif tar_file is not None:
+        elif tar_file is not None and tar_file != "":
             if not os.path.exists(tar_file):
                 raise ValueError(f"tar_file {tar_file} does not exist")
             kwargs["data"] = open(tar_file, "rb")

nextmv/cloud/run.py

@@ -470,6 +470,40 @@ class RunConfiguration(BaseModel):
     queuing: Optional[RunQueuing] = None
     """Queuing configuration for the run."""
 
+    def resolve(
+        self,
+        input: Union[Input, dict[str, Any], BaseModel, str],
+        dir_path: Optional[str] = None,
+    ) -> None:
+        """
+        Resolves the run configuration by modifying or setting the `format`,
+        based on the type of input that is provided.
+
+        Parameters
+        ----------
+        input : Input or dict[str, Any] or BaseModel or str, optional
+            The input to use for resolving the run configuration.
+        dir_path : str, optional
+            The directory path where inputs can be loaded from.
+        """
+
+        # If the value is set by the user, do not change it.
+        if self.format is not None:
+            return
+
+        self.format = Format(format_input=FormatInput(input_type=InputFormat.JSON))
+
+        if isinstance(input, dict):
+            self.format.format_input.input_type = InputFormat.JSON
+        elif isinstance(input, str):
+            self.format.format_input.input_type = InputFormat.TEXT
+        elif dir_path is not None and dir_path != "":
+            # Kinda hard to detect if we should be working with CSV_ARCHIVE or
+            # MULTI_FILE, so we default to MULTI_FILE.
+            self.format.format_input.input_type = InputFormat.MULTI_FILE
+        elif isinstance(input, Input):
+            self.format.format_input.input_type = input.input_format
+
 
 class ExternalRunResult(BaseModel):
     """

nextmv/input.py

@@ -108,7 +108,7 @@ class DataFile:
         the following arguments:
 
         - `file_path`: a `str` argument which is the location where this
-          solution will be read from. This includes the dir and name of the
+          data will be read from. This includes the dir and name of the
           file. As such, the `name` parameter of this class is going to be
           passed to the `reader` function, joined with the directory where the
           file will be read from.
@@ -134,7 +134,7 @@ class DataFile:
     following arguments:
 
     - `file_path`: a `str` argument which is the location where this
-       solution will be read from. This includes the dir and name of the
+       data will be read from. This includes the dir and name of the
        file. As such, the `name` parameter of this class is going to be
        passed to the `loader` function, joined with the directory where the
        file will be read from.
@@ -155,9 +155,24 @@ class DataFile:
     Optional positional arguments to pass to the loader function. This can be
     used to customize the behavior of the loader.
     """
+    input_data_key: Optional[str] = None
+    """
+    Use this parameter to set a custom key to represent your file.
+
+    When using `InputFormat.MULTI_FILE` as the `input_format` of the `Input`,
+    the data from the file is loaded to the `.data` parameter of the `Input`.
+    In that case, the type of `.data` is `dict[str, Any]`, where each key
+    represents the file name (with extension) and the value is the data that is
+    actually loaded from the file using the `loader` function. You can set a
+    custom key to represent your file by using this attribute.
+    """
 
 
-def json_data_file(name: str, json_configurations: Optional[dict[str, Any]] = None) -> DataFile:
+def json_data_file(
+    name: str,
+    json_configurations: Optional[dict[str, Any]] = None,
+    input_data_key: Optional[str] = None,
+) -> DataFile:
     """
     This is a convenience function to create a `DataFile` that reads JSON data.
 
@@ -173,6 +188,15 @@ def json_data_file(name: str, json_configurations: Optional[dict[str, Any]] = No
         Name of the data file. You don't need to include the `.json` extension.
     json_configurations : dict[str, Any], optional
         JSON-specific configurations for reading the data.
+    input_data_key : str, optional
+        A custom key to represent the data from this file.
+
+        When using `InputFormat.MULTI_FILE` as the `input_format` of the `Input`,
+        the data from the file is loaded to the `.data` parameter of the `Input`.
+        In that case, the type of `.data` is `dict[str, Any]`, where each key
+        represents the file name (with extension) and the value is the data that is
+        actually loaded from the file using the `loader` function. You can set a
+        custom key to represent your file by using this attribute.
 
     Returns
     -------
@@ -204,10 +228,15 @@ def json_data_file(name: str, json_configurations: Optional[dict[str, Any]] = No
     return DataFile(
         name=name,
         loader=loader,
+        input_data_key=input_data_key,
     )
 
 
-def csv_data_file(name: str, csv_configurations: Optional[dict[str, Any]] = None) -> DataFile:
+def csv_data_file(
+    name: str,
+    csv_configurations: Optional[dict[str, Any]] = None,
+    input_data_key: Optional[str] = None,
+) -> DataFile:
     """
     This is a convenience function to create a `DataFile` that reads CSV data.
 
@@ -223,6 +252,15 @@ def csv_data_file(name: str, csv_configurations: Optional[dict[str, Any]] = None
         Name of the data file. You don't need to include the `.csv` extension.
     csv_configurations : dict[str, Any], optional
         CSV-specific configurations for reading the data.
+    input_data_key : str, optional
+        A custom key to represent the data from this file.
+
+        When using `InputFormat.MULTI_FILE` as the `input_format` of the `Input`,
+        the data from the file is loaded to the `.data` parameter of the `Input`.
+        In that case, the type of `.data` is `dict[str, Any]`, where each key
+        represents the file name (with extension) and the value is the data that is
+        actually loaded from the file using the `loader` function. You can set a
+        custom key to represent your file by using this attribute.
 
     Returns
     -------
@@ -254,10 +292,11 @@ def csv_data_file(name: str, csv_configurations: Optional[dict[str, Any]] = None
     return DataFile(
         name=name,
         loader=loader,
+        input_data_key=input_data_key,
     )
 
 
-def text_data_file(name: str) -> DataFile:
+def text_data_file(name: str, input_data_key: Optional[str] = None) -> DataFile:
     """
     This is a convenience function to create a `DataFile` that reads utf-8
     encoded text data.
@@ -274,6 +313,15 @@ def text_data_file(name: str) -> DataFile:
     ----------
     name : str
         Name of the data file. The file extension must be provided in the name.
+    input_data_key : str, optional
+        A custom key to represent the data from this file.
+
+        When using `InputFormat.MULTI_FILE` as the `input_format` of the `Input`,
+        the data from the file is loaded to the `.data` parameter of the `Input`.
+        In that case, the type of `.data` is `dict[str, Any]`, where each key
+        represents the file name (with extension) and the value is the data that is
+        actually loaded from the file using the `loader` function. You can set a
+        custom key to represent your file by using this attribute.
 
     Returns
     -------
@@ -297,6 +345,7 @@ def text_data_file(name: str) -> DataFile:
     return DataFile(
         name=name,
         loader=loader,
+        input_data_key=input_data_key,
     )
 
 
@@ -311,18 +360,6 @@ class Input:
     from nextmv import Input
     ```
 
-    Parameters
-    ----------
-    data : Union[Union[dict[str, Any], Any], str, list[dict[str, Any]],
-    dict[str, list[dict[str, Any]]], dict[str, Any]]
-        The actual data.
-    input_format : InputFormat, optional
-        Format of the input data. Default is `InputFormat.JSON`.
-    options : Options, optional
-        Options that the input was created with.
-
-    Notes
-    -----
     The `data`'s type must match the `input_format`:
 
     - `InputFormat.JSON`: the data is `Union[dict[str, Any], Any]`. This just
@@ -340,6 +377,18 @@ class Input:
        from one or more files in a specific directory. Given that each file can
        be of different types (JSON, CSV, Excel, etc...), the data captured from
        each might vary. To reflect this, the data is loaded as a dict of items.
+       You can have a custom key for the data, that is not the file name,  if
+       you use the `input_data_key` parameter of the `DataFile` class.
+
+    Parameters
+    ----------
+    data : Union[Union[dict[str, Any], Any], str, list[dict[str, Any]],
+    dict[str, list[dict[str, Any]]], dict[str, Any]]
+        The actual data.
+    input_format : InputFormat, optional
+        Format of the input data. Default is `InputFormat.JSON`.
+    options : Options, optional
+        Options that the input was created with.
 
     Raises
     ------
@@ -888,7 +937,15 @@ class LocalInputLoader(InputLoader):
                 *data_file.loader_args,
                 **data_file.loader_kwargs,
             )
-            data[name] = d
+
+            key = name
+            if data_file.input_data_key is not None:
+                key = data_file.input_data_key
+
+            if data.get(key) is not None:
+                raise ValueError(f"Duplicate input data key found: {key}")
+
+            data[key] = d
 
         return data
 

nextmv/output.py

@@ -582,7 +582,7 @@ class SolutionFile:
     `csv.DictWriter`, then the data should be a list of dictionaries, where
     each dictionary represents a row in the CSV file.
     """
-    writer: Callable[[str, str, Any], None]
+    writer: Callable[[str, Any], None]
     """
     Callable that writes the solution data to the file. This should be a
     function implemented by the user. There are convenience functions that you

{nextmv-0.29.0.dev0.dist-info → nextmv-0.29.2.dev1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nextmv
-Version: 0.29.0.dev0
+Version: 0.29.2.dev1
 Summary: The all-purpose Python SDK for Nextmv
 Project-URL: Homepage, https://www.nextmv.io
 Project-URL: Documentation, https://nextmv-py.docs.nextmv.io/en/latest/nextmv/
@@ -225,6 +225,18 @@ Requires-Dist: requests>=2.31.0
 Requires-Dist: urllib3>=2.1.0
 Provides-Extra: all
 Requires-Dist: mlflow>=2.17.2; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: build>=1.0.3; extra == 'dev'
+Requires-Dist: mlflow>=2.19.0; extra == 'dev'
+Requires-Dist: nextroute>=1.11.1; extra == 'dev'
+Requires-Dist: openpyxl>=3.1.5; extra == 'dev'
+Requires-Dist: pandas>=2.2.3; extra == 'dev'
+Requires-Dist: pydantic>=2.5.2; extra == 'dev'
+Requires-Dist: pyyaml>=6.0.1; extra == 'dev'
+Requires-Dist: requests>=2.31.0; extra == 'dev'
+Requires-Dist: ruff>=0.1.7; extra == 'dev'
+Requires-Dist: twine>=4.0.2; extra == 'dev'
+Requires-Dist: urllib3>=2.1.0; extra == 'dev'
 Description-Content-Type: text/markdown
 
 # Nextmv Python SDK

{nextmv-0.29.0.dev0.dist-info → nextmv-0.29.2.dev1.dist-info}/RECORD

@@ -1,31 +1,31 @@
-nextmv/__about__.py,sha256=5Hyqy6YRmHjjJiH8zSsVktP7LyJJ_p94ZcbMBpGvTAo,29
+nextmv/__about__.py,sha256=GsQEf7UDs4W0bljhrNkXljBHxyv30ngFhMCbDaDHo-0,29
 nextmv/__entrypoint__.py,sha256=dA0iwwHtrq6Z9w9FxmxKLoBGLyhe7jWtUAU-Y3PEgHg,1094
 nextmv/__init__.py,sha256=FsF0pEkOSBuPY5EKu7NsBxro7jswGmOmaw61kZEudXY,1930
 nextmv/_serialization.py,sha256=JlSl6BL0M2Esf7F89GsGIZ__Pp8RnFRNM0UxYhuuYU4,2853
 nextmv/base_model.py,sha256=qmJ4AsYr9Yv01HQX_BERrn3229gyoZrYyP9tcyqNfeU,2311
 nextmv/deprecated.py,sha256=kEVfyQ-nT0v2ePXTNldjQG9uH5IlfQVy3L4tztIxwmU,1638
-nextmv/input.py,sha256=pen17zZtEdbTAIU4oOS7IlKffqSKnejYDO_EeFQid2s,37124
+nextmv/input.py,sha256=iTMIdhSi4H-Xot44CYaUH110WDcpWDsJ5JXxSMGIZaY,40030
 nextmv/logger.py,sha256=kNIbu46MisrzYe4T0hNMpWfRTKKacDVvbtQcNys_c_E,2513
 nextmv/model.py,sha256=SVoJLN_f5knXjaPLlyWWvzIqX_qKu1txn6pYfKPwt14,15019
 nextmv/options.py,sha256=-9ru7nzqMsFf0aAAfR5OuMvChXYT6aho5sGghHKu8Ds,37323
-nextmv/output.py,sha256=QE4A8AEusCb8asvJFOSSz9S6ICDxB619ykqAM71qnI0,54049
+nextmv/output.py,sha256=mBvxOshyizH9g2dc8Yp7iOwDCtFng_UnyTfzg14RMtQ,54044
 nextmv/cloud/__init__.py,sha256=7BCh3z-XkbIcMvFHmbj2wA8OquIovjrAZL7O9kA9VZc,3868
 nextmv/cloud/acceptance_test.py,sha256=Bcfdmh2fkPeBx8FDCngeUo2fjV_LhsUdygnzDQCDbYY,26898
 nextmv/cloud/account.py,sha256=eukiYQha4U2fkIjg4SgdoawKE1kU5G7GPyDJVrn8hHA,6064
-nextmv/cloud/application.py,sha256=YTtqN8r602r-rsjiLBbcq3gmu3v27CGfL3Bxg4lUPhQ,116324
+nextmv/cloud/application.py,sha256=qMf7N0DpJnnkJiyMYjqFjR_2fVzOTjqT-bUWShYg7XE,119766
 nextmv/cloud/batch_experiment.py,sha256=rD3m-ioE1G8ADYN7afzr7zlq-3H22TNlj9RAh-_ZqIo,7270
-nextmv/cloud/client.py,sha256=2TTr7oc5g7zpB64xrACDZZph189JpPmE_HiUzXnGATM,18146
+nextmv/cloud/client.py,sha256=E0DiUb377jvEnpXlRnfT1PGCI0Jm0lTUoX5VqeU91lk,18165
 nextmv/cloud/input_set.py,sha256=2dqmf5z-rZjTKwtBRvnUdfPfKv28It5uTCX0C70uP4Y,4242
 nextmv/cloud/instance.py,sha256=SS4tbp0LQMWDaeYpwcNxJei82oi_Hozv1t5i3QGjASY,4024
 nextmv/cloud/manifest.py,sha256=bphIZJzStkAc1gme39SecwI4L36QDjeyhWEZrSaukS4,35782
 nextmv/cloud/package.py,sha256=f0OjdlIOsI2LpmgSxdFf6YaA8Ucs9yAm_3bO0Cp8LH4,13027
-nextmv/cloud/run.py,sha256=zRPYeceNiuBMEcu-XZ2TUESn982HAUWGrwC2t13zHMg,19483
+nextmv/cloud/run.py,sha256=YPBVjbnc6Ebgjxm5Rw1eY2-MiYx3KC7fQyqKWXY9auY,20836
 nextmv/cloud/safe.py,sha256=idifvV8P_79Zo2hIC_qxqZt9LUmD5TLQ9ikKwRUvd34,2522
 nextmv/cloud/scenario.py,sha256=JRFTDiFBcrgud6wE2qDHUu5oO-Ur3zbPYhhB6ONCxTo,14263
 nextmv/cloud/secrets.py,sha256=fA5cX0jfTsPVZWV7433wzETGlXpWRLHGswuObx9e6FQ,6820
 nextmv/cloud/status.py,sha256=blvykRCTCTBkaqH88j4dzdQLhU2v1Ig62-_va98zw20,2789
 nextmv/cloud/version.py,sha256=5_S7_pWUVBFbvAArku20eK7S645GJcHtgE2OpXLdSzQ,5300
-nextmv-0.29.0.dev0.dist-info/METADATA,sha256=YrBM8nB7Hk944fot4aDYWMSkepo1qIvHv8w18M9LPIk,15307
-nextmv-0.29.0.dev0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-nextmv-0.29.0.dev0.dist-info/licenses/LICENSE,sha256=ZIbK-sSWA-OZprjNbmJAglYRtl5_K4l9UwAV3PGJAPc,11349
-nextmv-0.29.0.dev0.dist-info/RECORD,,
+nextmv-0.29.2.dev1.dist-info/METADATA,sha256=U0q6Eh7QzFYBNZx1GAtncOgdzf79v0O98TsBNYNl92Y,15831
+nextmv-0.29.2.dev1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+nextmv-0.29.2.dev1.dist-info/licenses/LICENSE,sha256=ZIbK-sSWA-OZprjNbmJAglYRtl5_K4l9UwAV3PGJAPc,11349
+nextmv-0.29.2.dev1.dist-info/RECORD,,