rapidata 2.14.1__py3-none-any.whl → 2.16.0__py3-none-any.whl

rapidata/rapidata_client/order/rapidata_order.py

@@ -70,6 +70,7 @@ class RapidataOrder:
 
         States:
             Created: The order has been created but not started yet.\n
+            Preview: The order has been set up and ready but not collecting responses 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
@@ -77,7 +78,7 @@ class RapidataOrder:
             Completed: The order has been completed.\n
             Failed: The order has failed.
         """
-        return self.__openapi_service.order_api.order_get_by_id_get(self.order_id).state
+        return self.__openapi_service.order_api.order_order_id_get(self.order_id).state
 
     def display_progress_bar(self, refresh_rate: int=5) -> None:
         """
@@ -125,7 +126,7 @@ class RapidataOrder:
         for _ in range(self._max_retries // 2):
             try:
                 workflow_id = self.__get_workflow_id()
-                progress = self.__openapi_service.workflow_api.workflow_get_progress_get(workflow_id)
+                progress = self.__openapi_service.workflow_api.workflow_workflow_id_progress_get(workflow_id)
                 break
             except Exception:
                 sleep(self._retry_delay * 2)
@@ -154,7 +155,7 @@ class RapidataOrder:
             sleep(5)
 
         try:
-            return RapidataResults(self.__openapi_service.order_api.order_get_order_results_get(id=self.order_id)) # type: ignore
+            return RapidataResults(json.loads(self.__openapi_service.order_api.order_order_id_download_results_get(order_id=self.order_id)))
         except (ApiException, json.JSONDecodeError) as e:
             raise Exception(f"Failed to get order results: {str(e)}") from e
         
@@ -164,12 +165,9 @@ class RapidataOrder:
         
         Raises:
             Exception: If the order is not in processing state.
-        """
-        if (status := self.get_status()) != OrderState.PROCESSING:
-            raise Exception(f"Preview only available if order is processing. current status: {status}")
-        
+        """        
         campaign_id = self.__get_campaign_id()
-        auth_url = f"https://rapids.{self.__openapi_service.enviroment}/preview/campaign?id={campaign_id}"
+        auth_url = f"https://app.{self.__openapi_service.enviroment}/order/detail/{self.order_id}/preview?campaignId={campaign_id}"
         could_open_browser = webbrowser.open(auth_url)
         if not could_open_browser:
             encoded_url = urllib.parse.quote(auth_url, safe="%/:=&?~#+!$,;'@()*[]")
@@ -180,7 +178,7 @@ class RapidataOrder:
         if not self.__pipeline_id:
             for _ in range(self._max_retries):
                 try:
-                    self.__pipeline_id = self.__openapi_service.order_api.order_get_by_id_get(self.order_id).pipeline_id
+                    self.__pipeline_id = self.__openapi_service.order_api.order_order_id_get(self.order_id).pipeline_id
                     break
                 except Exception:
                     sleep(self._retry_delay)
@@ -207,7 +205,7 @@ class RapidataOrder:
         pipeline_id = self.__get_pipeline_id()
         for _ in range(self._max_retries):
             try:
-                pipeline = self.__openapi_service.pipeline_api.pipeline_id_get(pipeline_id)
+                pipeline = self.__openapi_service.pipeline_api.pipeline_pipeline_id_get(pipeline_id)
                 self.__workflow_id = cast(WorkflowArtifactModel, pipeline.artifacts["workflow-artifact"].actual_instance).workflow_id
                 self.__campaign_id = cast(CampaignArtifactModel, pipeline.artifacts["campaign-artifact"].actual_instance).campaign_id
                 return

rapidata/rapidata_client/order/rapidata_order_manager.py

@@ -249,6 +249,7 @@ class RapidataOrderManager:
                              datapoints: list[str],
                              total_comparison_budget: int,
                              responses_per_comparison: int = 5,
+                             data_type: str = RapidataDataTypes.MEDIA,
                              random_comparisons_ratio: float = 0.5,
                              context: Optional[str] = None,
                              validation_set_id: Optional[str] = None,
@@ -265,6 +266,8 @@ class RapidataOrderManager:
             datapoints (list[str]): A list of datapoints that will participate in the ranking.
             total_comparison_budget (int): The total number of (pairwise-)comparisons that can be made.
             responses_per_comparison (int, optional): The number of responses collected per comparison.
+            data_type (str, optional): The data type of the datapoints. Defaults to RapidataDataTypes.MEDIA. \n
+                Other option: RapidataDataTypes.TEXT ("text").
             random_comparisons_ratio (float, optional): The fraction of random comparisons in the ranking process.
                 The rest will focus on pairing similarly ranked datapoints. Defaults to 0.5 and can be left untouched.
             context (str, optional): The context for all the comparison. Defaults to None.\n
@@ -276,7 +279,13 @@ class RapidataOrderManager:
             selections (Sequence[RapidataSelection], optional): The list of selections for the order. Defaults to None. Decides in what order the tasks should be shown.
         """
 
-        assets = [MediaAsset(path=path) for path in datapoints]
+        if data_type == RapidataDataTypes.MEDIA:
+            assets = [MediaAsset(path=path) for path in datapoints]
+        elif data_type == RapidataDataTypes.TEXT:
+            assets = [TextAsset(text=text) for text in datapoints]
+        else:
+            raise ValueError(f"Unsupported data type: {data_type}, must be one of {RapidataDataTypes._possible_values()}")
+
         return self._create_general_order(
             name=name,
             workflow=RankingWorkflow(
@@ -525,7 +534,7 @@ class RapidataOrderManager:
         """
 
         try:
-            order = self._openapi_service.order_api.order_get_by_id_get(order_id)
+            order = self._openapi_service.order_api.order_order_id_get(order_id)
         except Exception:
             raise ValueError(f"Order with ID {order_id} not found.")
 

rapidata/rapidata_client/order/rapidata_results.py

@@ -40,7 +40,7 @@ class RapidataResults(dict):
                 raise ValueError("No detailed results found in the data")
             return self._to_pandas_with_detailed_results()
             
-        if self["info"].get("orderType") == "Compare":
+        if self["info"].get("orderType") == "Compare" or self["info"].get("orderType") == "Ranking":
             return self._compare_to_pandas()
         
         # Get the structure from first item

rapidata/rapidata_client/validation/rapidata_validation_set.py

@@ -2,6 +2,7 @@ from rapidata.rapidata_client.validation.rapids.rapids import Rapid
 from rapidata.service.openapi_service import OpenAPIService
 from requests.adapters import HTTPAdapter, Retry
 import requests
+from rapidata.api_client.models.update_dimensions_model import UpdateDimensionsModel
 
 class RapidataValidationSet:
     """A class for interacting with a Rapidata validation set.
@@ -28,6 +29,16 @@ class RapidataValidationSet:
             rapid (Rapid): The Rapid to add to the validation set.
         """
         rapid._add_to_validation_set(self.id, self.__openapi_service, self.__session)
+        return self
+
+    def update_dimensions(self, dimensions: list[str] | None):
+        """Update the dimensions of the validation set.
+
+        Args:
+            dimensions (list[str]): The new dimensions of the validation set.
+        """
+        self.__openapi_service.validation_api.validation_validation_set_id_dimensions_patch(self.id, UpdateDimensionsModel(dimensions=dimensions) if dimensions else None)
+        return self
 
     def _get_session(self, max_retries: int = 5, max_workers: int = 10) -> requests.Session:   
         """Get a requests session with retry logic.

rapidata/rapidata_client/validation/rapids/rapids.py

@@ -15,10 +15,8 @@ from rapidata.api_client.models.add_validation_rapid_model_payload import (
 from rapidata.api_client.models.add_validation_rapid_model_truth import (
     AddValidationRapidModelTruth,
 )
+from rapidata.api_client.models.create_datapoint_from_files_model_metadata_inner import CreateDatapointFromFilesModelMetadataInner
 
-from rapidata.api_client.models.create_datapoint_from_urls_model import (
-    CreateDatapointFromUrlsModelMetadataInner,
-)
 from rapidata.service.openapi_service import OpenAPIService
 
 import requests
@@ -70,7 +68,7 @@ class Rapid():
             payload=AddValidationRapidModelPayload(self.payload),
             truth=AddValidationRapidModelTruth(self.truth),
             metadata=[
-              CreateDatapointFromUrlsModelMetadataInner(meta.to_model())
+              CreateDatapointFromFilesModelMetadataInner(meta.to_model())
               for meta in self.metadata
             ],
             randomCorrectProbability=self.randomCorrectProbability,
@@ -97,7 +95,7 @@ class Rapid():
           payload=AddValidationRapidModelPayload(self.payload),
           truth=AddValidationRapidModelTruth(self.truth),
           metadata=[
-              CreateDatapointFromUrlsModelMetadataInner(meta.to_model())
+              CreateDatapointFromFilesModelMetadataInner(meta.to_model())
               for meta in self.metadata
           ],
           randomCorrectProbability=self.randomCorrectProbability,

rapidata/rapidata_client/validation/validation_set_manager.py

@@ -38,8 +38,9 @@ class ValidationSetManager:
         truths: list[list[str]],
         data_type: str = RapidataDataTypes.MEDIA,
         contexts: list[str] | None = None,
-        print_confirmation: bool = True,
         explanations: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a classification validation set.
         
@@ -57,8 +58,9 @@ class ValidationSetManager:
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.\n
                 If provided has to be the same length as datapoints and will be shown in addition to the instruction and answer options. (Therefore will be different for each datapoint)
                 Will be match up with the datapoints using the list index.
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanations (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -95,7 +97,7 @@ class ValidationSetManager:
                 )
             )
 
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation, dimensions=dimensions)
 
     def create_compare_set(self,
         name: str,
@@ -104,8 +106,9 @@ class ValidationSetManager:
         truths: list[str],
         data_type: str = RapidataDataTypes.MEDIA,
         contexts: list[str] | None = None,
-        print_confirmation: bool = True,
         explanation: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a comparison validation set.
 
@@ -123,8 +126,9 @@ class ValidationSetManager:
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.\n
                 If provided has to be the same length as datapoints and will be shown in addition to the instruction and truth. (Therefore will be different for each datapoint)
                 Will be match up with the datapoints using the list index.
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanation (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -160,7 +164,7 @@ class ValidationSetManager:
                 )
             )
  
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
   
     def create_select_words_set(self,
         name: str,
@@ -170,8 +174,9 @@ class ValidationSetManager:
         sentences: list[str],
         required_precision: float = 1.0,
         required_completeness: float = 1.0,
-        print_confirmation: bool = True,
         explanation: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a select words validation set.
 
@@ -188,8 +193,9 @@ class ValidationSetManager:
                 Must be the same length as datapoints.
             required_precision (float, optional): The required precision for the labeler to get the rapid correct (minimum ratio of the words selected that need to be correct). Defaults to 1.0 (no wrong word can be selected).
             required_completeness (float, optional): The required completeness for the labeler to get the rapid correct (miminum ratio of total correct words selected). Defaults to 1.0 (all correct words need to be selected).
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanation (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -223,7 +229,7 @@ class ValidationSetManager:
                 )
             )
 
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
 
     def create_locate_set(self,
         name: str,
@@ -231,8 +237,9 @@ class ValidationSetManager:
         truths: list[list[Box]],
         datapoints: list[str],
         contexts: list[str] | None = None,
-        print_confirmation: bool = True,
         explanation: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a locate validation set.
 
@@ -245,8 +252,9 @@ class ValidationSetManager:
                     truths: [[Box(0, 0, 100, 100)], [Box(50, 50, 150, 150)]] -> first datapoint the object is in the top left corner, second datapoint the object is in the center
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanation (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -282,7 +290,7 @@ class ValidationSetManager:
                 )
             )
         
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
     
     def create_draw_set(self,
         name: str,
@@ -290,8 +298,9 @@ class ValidationSetManager:
         truths: list[list[Box]],
         datapoints: list[str],
         contexts: list[str] | None = None,
-        print_confirmation: bool = True,
         explanation: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a draw validation set.
 
@@ -304,8 +313,9 @@ class ValidationSetManager:
                     truths: [[Box(0, 0, 100, 100)], [Box(50, 50, 150, 150)]] -> first datapoint the object is in the top left corner, second datapoint the object is in the center
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanation (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -340,7 +350,7 @@ class ValidationSetManager:
                 )
             )
 
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
 
     def create_timestamp_set(self,
         name: str,
@@ -348,8 +358,9 @@ class ValidationSetManager:
         truths: list[list[tuple[int, int]]],
         datapoints: list[str],
         contexts: list[str] | None = None,
-        print_confirmation: bool = True,
         explanation: list[str | None] | None = None,
+        dimensions: list[str] | None = None,
+        print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a timestamp validation set.
 
@@ -363,8 +374,9 @@ class ValidationSetManager:
                     truths: [[(0, 10)], [(20, 30)]] -> first datapoint the correct interval is from 0 to 10, second datapoint the correct interval is from 20 to 30
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
-            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
             explanation (list[str | None], optional): The explanations for each datapoint. Will be given to the annotators in case the answer is wrong. Defaults to None.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
+            print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
             ```python
@@ -399,11 +411,12 @@ class ValidationSetManager:
                 )
             )
 
-        return self._submit(name=name, rapids=rapids, print_confirmation=print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
     
     def create_mixed_set(self,
         name: str,
         rapids: list[Rapid],
+        dimensions: list[str] | None = None,
         print_confirmation: bool = True
     ) -> RapidataValidationSet:
         """Create a validation set with a list of rapids.
@@ -411,10 +424,11 @@ class ValidationSetManager:
         Args:
             name (str): The name of the validation set. (will not be shown to the labeler)
             rapids (list[Rapid]): The list of rapids to add to the validation set.
+            dimensions (list[str] | None, optional): The dimensions of the validation set. If not provided will be set to the default dimensions.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
         """
 
-        return self._submit(name, rapids, print_confirmation)
+        return self._submit(name=name, rapids=rapids, dimensions=dimensions, print_confirmation=print_confirmation)
     
     def get_validation_set_by_id(self, validation_set_id: str) -> RapidataValidationSet:
         """Get a validation set by ID.
@@ -432,7 +446,7 @@ class ValidationSetManager:
         
         return RapidataValidationSet(validation_set_id, validation_set.name, self.__openapi_service)
 
-    def _submit(self, name: str, rapids: list[Rapid], print_confirmation: bool) -> RapidataValidationSet:
+    def _submit(self, name: str, rapids: list[Rapid], dimensions: list[str] | None, print_confirmation: bool) -> RapidataValidationSet:
         validation_set_id = (
             self.__openapi_service.validation_api.validation_create_validation_set_post(
                 name=name
@@ -456,7 +470,8 @@ class ValidationSetManager:
             print(f"Validation set '{name}' created with ID {validation_set_id}\n",
                   f"Now viewable under: https://app.{self.__openapi_service.enviroment}/validation-set/detail/{validation_set_id}",
                   sep="")
-            
+        
+        validation_set.update_dimensions(dimensions)
         return validation_set
 
 

rapidata/rapidata_client/workflow/_ranking_workflow.py

@@ -3,7 +3,7 @@ from rapidata.api_client.models.compare_workflow_model import CompareWorkflowMod
 from rapidata.rapidata_client.workflow._base_workflow import Workflow
 from rapidata.rapidata_client.metadata import PromptMetadata
 from rapidata.api_client.models.create_datapoint_from_urls_model import (
-    CreateDatapointFromUrlsModelMetadataInner,
+    CreateDatapointFromFilesModelMetadataInner,
 )
 
 
@@ -21,7 +21,7 @@ class RankingWorkflow(Workflow):
                  ):
         super().__init__(type="CompareWorkflowConfig")
 
-        self.context = [CreateDatapointFromUrlsModelMetadataInner(
+        self.context = [CreateDatapointFromFilesModelMetadataInner(
             PromptMetadata(context).to_model())
             ] if context else None
 

{rapidata-2.14.1.dist-info → rapidata-2.16.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rapidata
-Version: 2.14.1
+Version: 2.16.0
 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