rapidata 2.7.1__py3-none-any.whl → 2.8.0__py3-none-any.whl

rapidata/api_client/models/datapoint.py

@@ -18,7 +18,7 @@ import re  # noqa: F401
 import json
 
 from datetime import datetime
-from pydantic import BaseModel, ConfigDict, Field, StrictStr, field_validator
+from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr, field_validator
 from typing import Any, ClassVar, Dict, List, Optional
 from rapidata.api_client.models.datapoint_asset import DatapointAsset
 from typing import Optional, Set
@@ -29,13 +29,14 @@ class Datapoint(BaseModel):
     Datapoint
     """ # noqa: E501
     t: StrictStr = Field(description="Discriminator value for Datapoint", alias="_t")
+    sort_index: Optional[StrictInt] = Field(default=None, alias="sortIndex")
     asset: DatapointAsset
     dataset_id: StrictStr = Field(alias="datasetId")
     id: Optional[StrictStr] = None
     deletion_date: Optional[datetime] = Field(default=None, alias="deletionDate")
     deleter_id: Optional[StrictStr] = Field(default=None, alias="deleterId")
     created_at: Optional[datetime] = Field(default=None, alias="createdAt")
-    __properties: ClassVar[List[str]] = ["_t", "asset", "datasetId", "id", "deletionDate", "deleterId", "createdAt"]
+    __properties: ClassVar[List[str]] = ["_t", "sortIndex", "asset", "datasetId", "id", "deletionDate", "deleterId", "createdAt"]
 
     @field_validator('t')
     def t_validate_enum(cls, value):
@@ -86,6 +87,11 @@ class Datapoint(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of asset
         if self.asset:
             _dict['asset'] = self.asset.to_dict()
+        # set to None if sort_index (nullable) is None
+        # and model_fields_set contains the field
+        if self.sort_index is None and "sort_index" in self.model_fields_set:
+            _dict['sortIndex'] = None
+
         # set to None if deletion_date (nullable) is None
         # and model_fields_set contains the field
         if self.deletion_date is None and "deletion_date" in self.model_fields_set:
@@ -109,6 +115,7 @@ class Datapoint(BaseModel):
 
         _obj = cls.model_validate({
             "_t": obj.get("_t") if obj.get("_t") is not None else 'Datapoint',
+            "sortIndex": obj.get("sortIndex"),
             "asset": DatapointAsset.from_dict(obj["asset"]) if obj.get("asset") is not None else None,
             "datasetId": obj.get("datasetId"),
             "id": obj.get("id"),

rapidata/api_client/models/datapoint_metadata_model.py

@@ -17,8 +17,8 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List
+from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
+from typing import Any, ClassVar, Dict, List, Optional
 from rapidata.api_client.models.datapoint_metadata_model_metadata_inner import DatapointMetadataModelMetadataInner
 from typing import Optional, Set
 from typing_extensions import Self
@@ -29,7 +29,8 @@ class DatapointMetadataModel(BaseModel):
     """ # noqa: E501
     dataset_id: StrictStr = Field(description="The id of the dataset to create the datapoint in.", alias="datasetId")
     metadata: List[DatapointMetadataModelMetadataInner] = Field(description="The metadata of the datapoint.")
-    __properties: ClassVar[List[str]] = ["datasetId", "metadata"]
+    sort_index: Optional[StrictInt] = Field(default=None, description="The index will be used to keep the datapoints in order. Useful if upload is parallelized", alias="sortIndex")
+    __properties: ClassVar[List[str]] = ["datasetId", "metadata", "sortIndex"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -77,6 +78,11 @@ class DatapointMetadataModel(BaseModel):
                 if _item_metadata:
                     _items.append(_item_metadata.to_dict())
             _dict['metadata'] = _items
+        # set to None if sort_index (nullable) is None
+        # and model_fields_set contains the field
+        if self.sort_index is None and "sort_index" in self.model_fields_set:
+            _dict['sortIndex'] = None
+
         return _dict
 
     @classmethod
@@ -90,7 +96,8 @@ class DatapointMetadataModel(BaseModel):
 
         _obj = cls.model_validate({
             "datasetId": obj.get("datasetId"),
-            "metadata": [DatapointMetadataModelMetadataInner.from_dict(_item) for _item in obj["metadata"]] if obj.get("metadata") is not None else None
+            "metadata": [DatapointMetadataModelMetadataInner.from_dict(_item) for _item in obj["metadata"]] if obj.get("metadata") is not None else None,
+            "sortIndex": obj.get("sortIndex")
         })
         return _obj
 

rapidata/api_client/models/get_compare_ab_summary_result.py

@@ -0,0 +1,87 @@
+# coding: utf-8
+
+"""
+    Rapidata.Dataset
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)
+
+    The version of the OpenAPI document: v1
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictFloat, StrictInt
+from typing import Any, ClassVar, Dict, List, Union
+from typing import Optional, Set
+from typing_extensions import Self
+
+class GetCompareAbSummaryResult(BaseModel):
+    """
+    GetCompareAbSummaryResult
+    """ # noqa: E501
+    winner_counts: Dict[str, Union[StrictFloat, StrictInt]] = Field(alias="winnerCounts")
+    __properties: ClassVar[List[str]] = ["winnerCounts"]
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of GetCompareAbSummaryResult from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of GetCompareAbSummaryResult from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "winnerCounts": obj.get("winnerCounts")
+        })
+        return _obj
+
+

rapidata/api_client/models/order_model.py

@@ -29,7 +29,7 @@ class OrderModel(BaseModel):
     """ # noqa: E501
     id: StrictStr
     pipeline_id: StrictStr = Field(alias="pipelineId")
-    order_date: Optional[datetime] = Field(alias="orderDate")
+    order_date: Optional[datetime] = Field(default=None, alias="orderDate")
     customer_mail: StrictStr = Field(alias="customerMail")
     state: StrictStr
     order_name: StrictStr = Field(alias="orderName")

rapidata/api_client/models/preliminary_download_model.py

@@ -24,9 +24,9 @@ from typing_extensions import Self
 
 class PreliminaryDownloadModel(BaseModel):
     """
-    PreliminaryDownloadModel
+    The model for creating a preliminary download.
     """ # noqa: E501
-    send_email: Optional[StrictBool] = Field(default=True, alias="sendEmail")
+    send_email: Optional[StrictBool] = Field(default=True, description="Whether to email the user when the download is ready.", alias="sendEmail")
     __properties: ClassVar[List[str]] = ["sendEmail"]
 
     model_config = ConfigDict(

rapidata/api_client/models/query_validation_rapids_result.py

@@ -32,7 +32,7 @@ class QueryValidationRapidsResult(BaseModel):
     """ # noqa: E501
     id: StrictStr
     type: StrictStr
-    asset: Optional[QueryValidationRapidsResultAsset]
+    asset: Optional[QueryValidationRapidsResultAsset] = None
     truth: Optional[QueryValidationRapidsResultTruth] = None
     payload: QueryValidationRapidsResultPayload
     metadata: List[FileAssetModel1MetadataInner]

rapidata/api_client/models/read_bridge_token_keys_result.py

@@ -27,12 +27,12 @@ class ReadBridgeTokenKeysResult(BaseModel):
     ReadBridgeTokenKeysResult
     """ # noqa: E501
     t: StrictStr = Field(description="Discriminator value for ReadBridgeTokenKeysResult", alias="_t")
-    access_token: Optional[StrictStr] = Field(alias="accessToken")
-    expires_in: Optional[StrictInt] = Field(alias="expiresIn")
-    refresh_token: Optional[StrictStr] = Field(alias="refreshToken")
-    id_token: Optional[StrictStr] = Field(alias="idToken")
-    token_type: Optional[StrictStr] = Field(alias="tokenType")
-    scope: Optional[StrictStr]
+    access_token: Optional[StrictStr] = Field(default=None, alias="accessToken")
+    expires_in: Optional[StrictInt] = Field(default=None, alias="expiresIn")
+    refresh_token: Optional[StrictStr] = Field(default=None, alias="refreshToken")
+    id_token: Optional[StrictStr] = Field(default=None, alias="idToken")
+    token_type: Optional[StrictStr] = Field(default=None, alias="tokenType")
+    scope: Optional[StrictStr] = None
     __properties: ClassVar[List[str]] = ["_t", "accessToken", "expiresIn", "refreshToken", "idToken", "tokenType", "scope"]
 
     @field_validator('t')

rapidata/api_client/models/report_model.py

@@ -28,7 +28,7 @@ class ReportModel(BaseModel):
     """ # noqa: E501
     rapid_id: StrictStr = Field(alias="rapidId")
     issue: StrictStr
-    message: Optional[StrictStr]
+    message: Optional[StrictStr] = None
     __properties: ClassVar[List[str]] = ["rapidId", "issue", "message"]
 
     @field_validator('issue')

rapidata/api_client/models/simple_workflow_model1.py

@@ -30,12 +30,12 @@ class SimpleWorkflowModel1(BaseModel):
     """ # noqa: E501
     t: StrictStr = Field(description="Discriminator value for SimpleWorkflowModel", alias="_t")
     id: StrictStr
-    dataset_id: Optional[StrictStr] = Field(alias="datasetId")
+    dataset_id: Optional[StrictStr] = Field(default=None, alias="datasetId")
     state: StrictStr
     blueprint: ValidationImportPostRequestBlueprint
     referee: CompareWorkflowModel1Referee
     name: StrictStr
-    owner_mail: Optional[StrictStr] = Field(alias="ownerMail")
+    owner_mail: Optional[StrictStr] = Field(default=None, alias="ownerMail")
     __properties: ClassVar[List[str]] = ["_t", "id", "datasetId", "state", "blueprint", "referee", "name", "ownerMail"]
 
     @field_validator('t')

rapidata/api_client/models/update_campaign_model.py

@@ -26,8 +26,8 @@ class UpdateCampaignModel(BaseModel):
     """
     The model containing the new configuration for a campaign.
     """ # noqa: E501
-    priority: Optional[StrictInt] = Field(description="A value above 0 indicating how much the campaign should be prioritized.  The higher the value the more weight it will be given during campaign selection.")
-    feature_flags: Optional[Dict[str, StrictStr]] = Field(description="The feature flags to assign this campaign.", alias="featureFlags")
+    priority: Optional[StrictInt] = Field(default=None, description="A value above 0 indicating how much the campaign should be prioritized.  The higher the value the more weight it will be given during campaign selection.")
+    feature_flags: Optional[Dict[str, StrictStr]] = Field(default=None, description="The feature flags to assign this campaign.", alias="featureFlags")
     __properties: ClassVar[List[str]] = ["priority", "featureFlags"]
 
     model_config = ConfigDict(

rapidata/api_client/models/update_validation_rapid_model.py

@@ -28,8 +28,8 @@ class UpdateValidationRapidModel(BaseModel):
     The model for updating a validation rapid.
     """ # noqa: E501
     truth: UpdateValidationRapidModelTruth
-    explanation: Optional[StrictStr]
-    prompt: Optional[StrictStr]
+    explanation: Optional[StrictStr] = None
+    prompt: Optional[StrictStr] = None
     __properties: ClassVar[List[str]] = ["truth", "explanation", "prompt"]
 
     model_config = ConfigDict(

rapidata/api_client/models/upload_files_from_s3_bucket_model.py

@@ -28,10 +28,10 @@ class UploadFilesFromS3BucketModel(BaseModel):
     """ # noqa: E501
     dataset_id: StrictStr = Field(description="The id of the dataset to upload the files to.", alias="datasetId")
     bucket_name: StrictStr = Field(description="The name of the S3 bucket to upload the files from.", alias="bucketName")
-    region: Optional[StrictStr] = Field(description="The region of the S3 bucket.")
+    region: Optional[StrictStr] = Field(default=None, description="The region of the S3 bucket.")
     source_prefix: StrictStr = Field(description="The prefix of the files to upload.", alias="sourcePrefix")
-    access_key: Optional[StrictStr] = Field(description="The access key to use for the S3 bucket.", alias="accessKey")
-    secret_key: Optional[StrictStr] = Field(description="The secret key to use for the S3 bucket.", alias="secretKey")
+    access_key: Optional[StrictStr] = Field(default=None, description="The access key to use for the S3 bucket.", alias="accessKey")
+    secret_key: Optional[StrictStr] = Field(default=None, description="The secret key to use for the S3 bucket.", alias="secretKey")
     use_custom_aws_credentials: StrictBool = Field(description="Whether to use custom AWS credentials.", alias="useCustomAwsCredentials")
     clear_dataset: StrictBool = Field(description="Whether to clear the dataset before uploading the files.", alias="clearDataset")
     __properties: ClassVar[List[str]] = ["datasetId", "bucketName", "region", "sourcePrefix", "accessKey", "secretKey", "useCustomAwsCredentials", "clearDataset"]

rapidata/api_client/models/upload_text_sources_to_dataset_model.py

@@ -17,8 +17,8 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List
+from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
+from typing import Any, ClassVar, Dict, List, Optional
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -28,7 +28,8 @@ class UploadTextSourcesToDatasetModel(BaseModel):
     """ # noqa: E501
     dataset_id: StrictStr = Field(description="The id of the dataset to upload the text sources to.", alias="datasetId")
     text_sources: List[StrictStr] = Field(description="The text sources to upload.", alias="textSources")
-    __properties: ClassVar[List[str]] = ["datasetId", "textSources"]
+    sort_index: Optional[StrictInt] = Field(default=None, description="The index will be used to keep the datapoints in order. Useful if upload is parallelized", alias="sortIndex")
+    __properties: ClassVar[List[str]] = ["datasetId", "textSources", "sortIndex"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -69,6 +70,11 @@ class UploadTextSourcesToDatasetModel(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
+        # set to None if sort_index (nullable) is None
+        # and model_fields_set contains the field
+        if self.sort_index is None and "sort_index" in self.model_fields_set:
+            _dict['sortIndex'] = None
+
         return _dict
 
     @classmethod
@@ -82,7 +88,8 @@ class UploadTextSourcesToDatasetModel(BaseModel):
 
         _obj = cls.model_validate({
             "datasetId": obj.get("datasetId"),
-            "textSources": obj.get("textSources")
+            "textSources": obj.get("textSources"),
+            "sortIndex": obj.get("sortIndex")
         })
         return _obj
 

rapidata/api_client_README.md

@@ -90,9 +90,7 @@ Class | Method | HTTP request | Description
 *DatasetApi* | [**dataset_get_by_id_get**](rapidata/api_client/docs/DatasetApi.md#dataset_get_by_id_get) | **GET** /Dataset/GetById | Gets a dataset by its id.
 *DatasetApi* | [**dataset_import_post**](rapidata/api_client/docs/DatasetApi.md#dataset_import_post) | **POST** /Dataset/Import | Imports datapoints from a csv file.
 *DatasetApi* | [**dataset_update_name_post**](rapidata/api_client/docs/DatasetApi.md#dataset_update_name_post) | **POST** /Dataset/UpdateName | Updates the name of a dataset.
-*DatasetApi* | [**dataset_upload_datapoint_post**](rapidata/api_client/docs/DatasetApi.md#dataset_upload_datapoint_post) | **POST** /Dataset/UploadDatapoint | Creates a new multi asset datapoint.
 *DatasetApi* | [**dataset_upload_files_from_s3_post**](rapidata/api_client/docs/DatasetApi.md#dataset_upload_files_from_s3_post) | **POST** /Dataset/UploadFilesFromS3 | Uploads files from an S3 bucket to a dataset.
-*DatasetApi* | [**dataset_upload_images_to_dataset_post**](rapidata/api_client/docs/DatasetApi.md#dataset_upload_images_to_dataset_post) | **POST** /Dataset/UploadImagesToDataset | Uploads images to a dataset.
 *IdentityApi* | [**identity_create_bridge_token_post**](rapidata/api_client/docs/IdentityApi.md#identity_create_bridge_token_post) | **POST** /Identity/CreateBridgeToken | Creates a pair of read and write keys for a client.  The write key is used to store the authentication result.  The read key is used to retrieve the authentication result.
 *IdentityApi* | [**identity_read_bridge_token_get**](rapidata/api_client/docs/IdentityApi.md#identity_read_bridge_token_get) | **GET** /Identity/ReadBridgeToken | Tries to read the bridge token keys for a given read key.  The read key is used to retrieve the authentication result written by the write key.
 *IdentityApi* | [**identity_register_temporary_post**](rapidata/api_client/docs/IdentityApi.md#identity_register_temporary_post) | **POST** /Identity/RegisterTemporary | Registers and logs in a temporary customer.
@@ -129,6 +127,7 @@ Class | Method | HTTP request | Description
 *RapidApi* | [**rapid_add_user_guess_post**](rapidata/api_client/docs/RapidApi.md#rapid_add_user_guess_post) | **POST** /Rapid/AddUserGuess | Submits a user guess for a Rapid.
 *RapidApi* | [**rapid_create_demographic_rapid_post**](rapidata/api_client/docs/RapidApi.md#rapid_create_demographic_rapid_post) | **POST** /Rapid/CreateDemographicRapid | Creates a new Demographic Rapid.
 *RapidApi* | [**rapid_query_validation_rapids_get**](rapidata/api_client/docs/RapidApi.md#rapid_query_validation_rapids_get) | **GET** /Rapid/QueryValidationRapids | Queries the validation rapids for a specific validation set.
+*RapidApi* | [**rapid_rapid_id_delete**](rapidata/api_client/docs/RapidApi.md#rapid_rapid_id_delete) | **DELETE** /rapid/{rapidId} | Deletes a rapid.
 *RapidApi* | [**rapid_report_post**](rapidata/api_client/docs/RapidApi.md#rapid_report_post) | **POST** /Rapid/Report | Used to report an issue with a rapid.
 *RapidApi* | [**rapid_skip_user_guess_post**](rapidata/api_client/docs/RapidApi.md#rapid_skip_user_guess_post) | **POST** /Rapid/SkipUserGuess | Skips a Rapid for the user.
 *RapidApi* | [**rapid_validate_current_rapid_bag_get**](rapidata/api_client/docs/RapidApi.md#rapid_validate_current_rapid_bag_get) | **GET** /Rapid/ValidateCurrentRapidBag | Validates that the rapids associated with the current user are active.
@@ -147,6 +146,7 @@ Class | Method | HTTP request | Description
 *WorkflowApi* | [**workflow_delete_delete**](rapidata/api_client/docs/WorkflowApi.md#workflow_delete_delete) | **DELETE** /Workflow/Delete | Deletes a workflow.
 *WorkflowApi* | [**workflow_get_by_id_get**](rapidata/api_client/docs/WorkflowApi.md#workflow_get_by_id_get) | **GET** /Workflow/GetById | Get a workflow by its ID.
 *WorkflowApi* | [**workflow_get_progress_get**](rapidata/api_client/docs/WorkflowApi.md#workflow_get_progress_get) | **GET** /Workflow/GetProgress | Get the progress of a workflow.
+*WorkflowApi* | [**workflow_id_compare_ab_summary_get**](rapidata/api_client/docs/WorkflowApi.md#workflow_id_compare_ab_summary_get) | **GET** /workflow/{id}/compare-ab-summary | Calculates a summary of the results for a simple compare workflow.  The summary includes the number of times an asset at each index was the winner.
 *WorkflowApi* | [**workflow_query_get**](rapidata/api_client/docs/WorkflowApi.md#workflow_query_get) | **GET** /Workflow/Query | Queries workflows based on the provided filter, page, and sort criteria.
 
 
@@ -262,6 +262,7 @@ Class | Method | HTTP request | Description
  - [Gender](rapidata/api_client/docs/Gender.md)
  - [GenderUserFilterModel](rapidata/api_client/docs/GenderUserFilterModel.md)
  - [GetAvailableValidationSetsResult](rapidata/api_client/docs/GetAvailableValidationSetsResult.md)
+ - [GetCompareAbSummaryResult](rapidata/api_client/docs/GetCompareAbSummaryResult.md)
  - [GetCompareWorkflowResultsModel](rapidata/api_client/docs/GetCompareWorkflowResultsModel.md)
  - [GetCompareWorkflowResultsResult](rapidata/api_client/docs/GetCompareWorkflowResultsResult.md)
  - [GetCompareWorkflowResultsResultAsset](rapidata/api_client/docs/GetCompareWorkflowResultsResultAsset.md)

rapidata/rapidata_client/assets/_media_asset.py

@@ -1,6 +1,7 @@
-"""Media Asset Module
+"""Media Asset Module with Lazy Loading
 
 Defines the MediaAsset class for handling media file paths within assets.
+Implements lazy loading for URL-based media to prevent unnecessary downloads.
 """
 
 import os
@@ -12,18 +13,20 @@ from PIL import Image
 from tinytag import TinyTag
 import tempfile
 from pydantic import StrictStr, StrictBytes
-from typing import Optional
+from typing import Optional, cast
 import logging
+from functools import cached_property
 
 
 class MediaAsset(BaseAsset):
-    """MediaAsset Class
+    """MediaAsset Class with Lazy Loading
 
-    Represents a media asset by storing the file path.
+    Represents a media asset by storing the file path or URL.
+    Only downloads URL content when needed.
     Supports local files and URLs for images, MP3, and MP4.
 
     Args:
-        path (str): The file system path to the media asset.
+        path (str): The file system path to the media asset or URL.
 
     Raises:
         FileNotFoundError: If the provided file path does not exist.
@@ -67,23 +70,40 @@ class MediaAsset(BaseAsset):
 
         Raises:
             FileNotFoundError: If the provided file path does not exist.
-            ValueError: If media type is unsupported or duration exceeds 25 seconds.
+            ValueError: If path is not a string.
         """
         if not isinstance(path, str):
             raise ValueError("Media must be a string, either a local file path or a URL")
         
+        self._url = None
+        self._content = None
+        
         if re.match(r'^https?://', path):
-            self.path = self.__get_media_bytes(path)
+            self._url = path
             self.name = path.split('/')[-1]
             self.name = self.__check_name_ending(self.name)
+            self.path = None  # Will be set when content is downloaded
             return
         
         if not os.path.exists(path):
             raise FileNotFoundError(f"File not found: {path}")
         
-        self.path: str | bytes = path
+        self.path = path
         self.name = path
 
+    @cached_property
+    def content(self) -> bytes:
+        """
+        Lazy loader for URL content. Only downloads when first accessed.
+        Uses cached_property to store the result after first download.
+        """
+        if self._url is None:
+            self.path = cast(str, self.path)
+            with open(self.path, 'rb') as f:
+                return f.read()
+            
+        return self.__get_media_bytes(self._url)
+
     def get_duration(self) -> int:
         """
         Get the duration of audio/video files in milliseconds.
@@ -97,27 +117,22 @@ class MediaAsset(BaseAsset):
         """
         path_to_check = self.name.lower()
         
-        # Return 0 for other static images
+        # Return 0 for static images
         if any(path_to_check.endswith(ext) for ext in ('.jpg', '.jpeg', '.png', '.webp', '.gif')):
             return 0
 
         try:
-            # For URL downloads (bytes), write to temporary file first
-            if isinstance(self.path, bytes):
-                with tempfile.NamedTemporaryFile(suffix=os.path.splitext(self.name)[1], delete=False) as tmp:
-                    tmp.write(self.path)
-                    tmp.flush()
-                    # Close the file so it can be read
-                    tmp_path = tmp.name
+            # Create temporary file from content
+            with tempfile.NamedTemporaryFile(suffix=os.path.splitext(self.name)[1], delete=False) as tmp:
+                tmp.write(self.content)
+                tmp.flush()
+                tmp_path = tmp.name
                 
                 try:
                     tag = TinyTag.get(tmp_path)
                 finally:
                     # Clean up the temporary file
                     os.unlink(tmp_path)
-            else:
-                # For local files, use path directly
-                tag = TinyTag.get(self.path)
             
             if tag.duration is None:
                 raise ValueError("Could not read duration from file")
@@ -136,17 +151,14 @@ class MediaAsset(BaseAsset):
             return None
             
         try:
-            if isinstance(self.path, bytes):
-                img = Image.open(BytesIO(self.path))
-            else:
-                img = Image.open(self.path)
+            img = Image.open(BytesIO(self.content))
             return img.size
         except Exception:
             return None
 
     def set_custom_name(self, name: str) -> 'MediaAsset':
         """Set a custom name for the media asset (only works with URLs)."""
-        if isinstance(self.path, bytes):
+        if self._url is not None:
             self.name = self.__check_name_ending(name)
         else:
             raise ValueError("Custom name can only be set for URLs.")
@@ -265,8 +277,10 @@ class MediaAsset(BaseAsset):
         self._logger.error(error_msg)
         raise ValueError(error_msg)
     
-    def to_file(self) -> StrictStr | tuple[StrictStr, StrictBytes] | StrictBytes: # types for autogenerated models
-        if isinstance(self.path, str):
+    def to_file(self) -> StrictStr | tuple[StrictStr, StrictBytes] | StrictBytes:
+        """Convert the media asset to a file representation."""
+        if self._url is None:
+            self.path = cast(str, self.path)
             return self.path
-        else: # isinstance(self.path, bytes)
-            return (self.name, self.path)
+        else:
+            return (self.name, self.content)

rapidata/rapidata_client/order/_rapidata_dataset.py

@@ -36,7 +36,7 @@ class RapidataDataset:
                     isinstance(asset, TextAsset) for asset in text_asset.assets
                 ), "All assets in a MultiAsset must be of type TextAsset."
 
-        def upload_text_datapoint(text_asset: TextAsset | MultiAsset) -> None:
+        def upload_text_datapoint(text_asset: TextAsset | MultiAsset, index: int) -> None:
             if isinstance(text_asset, TextAsset):
                 texts = [text_asset.text]
             elif isinstance(text_asset, MultiAsset):
@@ -46,7 +46,8 @@ class RapidataDataset:
 
             model = UploadTextSourcesToDatasetModel(
                 datasetId=self.dataset_id,
-                textSources=texts
+                textSources=texts,
+                sortIndex=index,
             )
 
             upload_response = self.openapi_service.dataset_api.dataset_creat_text_datapoint_post(model)
@@ -57,8 +58,8 @@ class RapidataDataset:
         total_uploads = len(text_assets)
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             futures = [
-                executor.submit(upload_text_datapoint, text_asset)
-                for text_asset in text_assets
+                executor.submit(upload_text_datapoint, text_asset, index=i)
+                for i, text_asset in enumerate(text_assets)
             ]
 
             with tqdm(total=total_uploads, desc="Uploading text datapoints") as pbar:
@@ -83,7 +84,7 @@ class RapidataDataset:
                     isinstance(asset, MediaAsset) for asset in media_path.assets
                 ), "All assets in a MultiAsset must be of type MediaAsset."
 
-        def upload_datapoint(media_asset: MediaAsset | MultiAsset, meta: Metadata | None) -> None:
+        def upload_datapoint(media_asset: MediaAsset | MultiAsset, meta: Metadata | None, index: int) -> None:
             if isinstance(media_asset, MediaAsset):
                 assets = [media_asset]
             elif isinstance(media_asset, MultiAsset):
@@ -99,6 +100,7 @@ class RapidataDataset:
                     if meta_model
                     else []
                 ),
+                sortIndex=index,
             )
 
             files: list[tuple[StrictStr, StrictBytes] | StrictStr | StrictBytes] = []
@@ -116,8 +118,8 @@ class RapidataDataset:
         total_uploads = len(media_paths)
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             futures = [
-                executor.submit(upload_datapoint, media_asset, meta)
-                for media_asset, meta in zip_longest(media_paths, metadata or [])
+                executor.submit(upload_datapoint, media_asset, meta, index=i)
+                for i, (media_asset, meta) in enumerate(zip_longest(media_paths, metadata or []))
             ]
 
             with tqdm(total=total_uploads, desc="Uploading datapoints") as pbar:

rapidata/rapidata_client/order/rapidata_order.py

@@ -65,6 +65,15 @@ class RapidataOrder:
     def get_status(self) -> str:
         """
         Gets the status of the order.
+
+        Different states are:
+            Created: The order has been created but not started yet.\n
+            Submitted: The order has been submitted and is being reviewed.\n
+            ManualReview: The order is in manual review - something went wrong with the automatic approval.\n
+            Processing: The order is actively being processed.\n
+            Paused: The order has been paused.\n
+            Completed: The order has been completed.\n
+            Failed: The order has failed.
         
         Returns: 
             The status of the order.

rapidata/rapidata_client/order/rapidata_order_manager.py

@@ -36,6 +36,8 @@ from rapidata.api_client.models.root_filter import RootFilter
 from rapidata.api_client.models.filter import Filter
 from rapidata.api_client.models.sort_criterion import SortCriterion
 
+from tqdm import tqdm
+
 
 class RapidataOrderManager:
     """
@@ -444,7 +446,7 @@ class RapidataOrderManager:
 
         assets = [MediaAsset(path=path) for path in datapoints]
 
-        for asset in assets:
+        for asset in tqdm(assets, desc="Downloading assets and checking duration"):
             if not asset.get_duration():
                 raise ValueError("The datapoints for this order must have a duration. (e.g. video or audio)")
 

rapidata/rapidata_client/validation/validation_set_manager.py

@@ -15,6 +15,7 @@ from urllib3._collections import HTTPHeaderDict
 from rapidata.rapidata_client.validation.rapids.box import Box
 
 from rapidata.api_client.models.query_validation_set_model import QueryValidationSetModel
+from tqdm import tqdm
 
 
 class ValidationSetManager:
@@ -404,7 +405,7 @@ class ValidationSetManager:
             openapi_service=self.__openapi_service
         )
 
-        for rapid in rapids:
+        for rapid in tqdm(rapids, desc="Uploading validation tasks"):
             validation_set.add_rapid(rapid)
         
         return validation_set

{rapidata-2.7.1.dist-info → rapidata-2.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rapidata
-Version: 2.7.1
+Version: 2.8.0
 Summary: Rapidata package containing the Rapidata Python Client to interact with the Rapidata Web API in an easy way.
 License: Apache-2.0
 Author: Rapidata AG