rapidata 2.24.1__tar.gz → 2.24.3__tar.gz

{rapidata-2.24.1 → rapidata-2.24.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rapidata
-Version: 2.24.1
+Version: 2.24.3
 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

{rapidata-2.24.1 → rapidata-2.24.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rapidata"
-version = "2.24.1"
+version = "2.24.3"
 description = "Rapidata package containing the Rapidata Python Client to interact with the Rapidata Web API in an easy way."
 authors = ["Rapidata AG <info@rapidata.ai>"]
 license = "Apache-2.0"

{rapidata-2.24.1 → rapidata-2.24.3}/src/rapidata/rapidata_client/filter/rapidata_filters.py

@@ -1,6 +1,5 @@
 from rapidata.rapidata_client.filter import (
     AgeFilter, 
-    CampaignFilter, 
     CountryFilter, 
     GenderFilter, 
     LanguageFilter, 
@@ -21,7 +20,6 @@ class RapidataFilters:
     Attributes:
         user_score (UserScoreFilter): The UserScoreFilter instance.
         age (AgeFilter): The AgeFilter instance.
-        campaign (CampaignFilter): The CampaignFilter instance.
         country (CountryFilter): The CountryFilter instance.
         gender (GenderFilter): The GenderFilter instance.
         language (LanguageFilter): The LanguageFilter instance.
@@ -38,7 +36,6 @@ class RapidataFilters:
     """
     user_score = UserScoreFilter
     age = AgeFilter 
-    campaign = CampaignFilter
     country = CountryFilter
     gender = GenderFilter
     language = LanguageFilter

{rapidata-2.24.1 → rapidata-2.24.3}/src/rapidata/rapidata_client/order/_rapidata_dataset.py

@@ -69,9 +69,6 @@ class RapidataDataset:
 
             upload_response = self.openapi_service.dataset_api.dataset_dataset_id_datapoints_texts_post(dataset_id=self.dataset_id, create_datapoint_from_text_sources_model=model)
 
-            if upload_response.errors:
-                raise ValueError(f"Error uploading text datapoint: {upload_response.errors}")
-
         total_uploads = len(text_assets)
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             futures = [
@@ -153,12 +150,6 @@ class RapidataDataset:
                         sortIndex=index
                     ),
                 )
-                
-            if upload_response.errors:
-                error_msg = f"Error uploading datapoint: {upload_response.errors}"
-                logger.error(error_msg)
-                local_failed.extend(identifiers_to_track)
-                raise ValueError(error_msg)
 
             local_successful.extend(identifiers_to_track)
 

{rapidata-2.24.1 → rapidata-2.24.3}/src/rapidata/rapidata_client/order/rapidata_order_manager.py

@@ -102,7 +102,6 @@ class RapidataOrderManager:
                 max_vote_count=responses_per_datapoint,
             )
 
-
         order_builder = RapidataOrderBuilder(name=name, openapi_service=self._openapi_service)
 
         if selections and validation_set_id:
@@ -159,7 +158,10 @@ class RapidataOrderManager:
             private_notes: list[str] | None = None,
         ) -> RapidataOrder:
         """Create a classification order.
-        
+
+        With this order you can have a datapoint (image, text, video, audio) be classified into one of the answer options.
+        Each response will be exactly one of the answer options.
+
         Args:
             name (str): The name of the order. (Will not be shown to the labeler)
             instruction (str): The instruction for how the data should be classified.
@@ -227,6 +229,8 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a compare order.
 
+        With this order you compare two datapoints (image, text, video, audio) and the annotators will choose one of the two based on the instruction.
+
         Args:
             name (str): The name of the order. (Will not be shown to the labeler)
             instruction (str): The instruction for the comparison. Will be shown along side each datapoint.
@@ -252,6 +256,12 @@ class RapidataOrderManager:
                 This will NOT be shown to the labelers but will be included in the result purely for your own reference.
         """
 
+        if any(type(datapoint) != list for datapoint in datapoints):
+            raise ValueError("Each datapoint must be a list of 2 paths/texts")
+
+        if any(len(datapoint) != 2 for datapoint in datapoints):
+            raise ValueError("Each datapoint must contain exactly two options")
+
         if data_type == RapidataDataTypes.MEDIA:
             assets = [MultiAsset([MediaAsset(path=path) for path in datapoint]) for datapoint in datapoints]
         elif data_type == RapidataDataTypes.TEXT:
@@ -293,6 +303,9 @@ class RapidataOrderManager:
         """
         Create a ranking order.
 
+        With this order you can rank a list of datapoints (image, text, video, audio) based on the instruction.
+        The annotators will be shown two datapoints at a time. The ranking happens in terms of an elo system based on the matchup results.
+
         Args:
             name (str): The name of the order.
             instruction (str): The question asked from People when They see two datapoints.
@@ -348,6 +361,9 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a free text order.
 
+        With this order you can have a datapoint (image, text, video, audio) be labeled with free text.
+        The annotators will be shown a datapoint and will be asked to answer a question with free text.
+
         Args:
             name (str): The name of the order.
             instruction (str): The instruction to answer with free text. Will be shown along side each datapoint.
@@ -398,6 +414,10 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a select words order.
 
+        With this order you can have a datapoint (image, text, video, audio) be labeled with a list of words.
+        The annotators will be shown a datapoint as well as a list of sentences split up by spaces.
+        They will then select specific words based on the instruction.
+
         Args:
             name (str): The name of the order.
             instruction (str): The instruction for how the words should be selected. Will be shown along side each datapoint.
@@ -448,6 +468,9 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a locate order.
 
+        With this order you can have people locate specific objects in a datapoint (image, text, video, audio).
+        The annotators will be shown a datapoint and will be asked to select locations based on the instruction.
+
         Args:
             name (str): The name of the order.
             instruction (str): The instruction what should be located. Will be shown along side each datapoint.
@@ -499,6 +522,9 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a draw order.
 
+        With this order you can have people draw lines on a datapoint (image, text, video, audio).
+        The annotators will be shown a datapoint and will be asked to draw lines based on the instruction.
+
         Args:
             name (str): The name of the order.
             instruction (str): The instruction for how the lines should be drawn. Will be shown along side each datapoint.
@@ -550,6 +576,12 @@ class RapidataOrderManager:
         ) -> RapidataOrder:
         """Create a timestamp order.
 
+        Warning: 
+            This order is currently not fully supported and may give unexpected results.
+
+        With this order you can have people mark specific timestamps in a datapoint (video, audio).
+        The annotators will be shown a datapoint and will be asked to select a timestamp based on the instruction.
+
         Args:
             name (str): The name of the order.
             instruction (str): The instruction for the timestamp task. Will be shown along side each datapoint.
@@ -602,39 +634,29 @@ class RapidataOrderManager:
         Returns:
             RapidataOrder: The Order instance.
         """
-
-        try:
-            order = self._openapi_service.order_api.order_order_id_get(order_id)
-        except Exception:
-            raise ValueError(f"Order with ID {order_id} not found.")
+        
+        order = self._openapi_service.order_api.order_order_id_get(order_id)
 
         return RapidataOrder(
             order_id=order_id, 
             name=order.order_name,
             openapi_service=self._openapi_service)
 
-    def find_orders(self, name: str = "", amount: int = 1) -> list[RapidataOrder]:
+    def find_orders(self, name: str = "", amount: int = 10) -> list[RapidataOrder]:
         """Find your recent orders given criteria. If nothing is provided, it will return the most recent order.
 
         Args:
             name (str, optional): The name of the order - matching order will contain the name. Defaults to "" for any order.
-            amount (int, optional): The amount of orders to return. Defaults to 1.
+            amount (int, optional): The amount of orders to return. Defaults to 10.
 
         Returns:
             list[RapidataOrder]: A list of RapidataOrder instances.
         """
-        try:
-            order_page_result = self._openapi_service.order_api.orders_get(QueryModel(
-                page=PageInfo(index=1, size=amount),
-                filter=RootFilter(filters=[Filter(field="OrderName", operator="Contains", value=name)]),
-                sortCriteria=[SortCriterion(direction="Desc", propertyName="OrderDate")]
-                ))
-
-        except BadRequestException as e:
-            raise ValueError(f"Error occured during request. \nError: {e.body} \nTraceid: {e.headers.get('X-Trace-Id') if isinstance(e.headers, HTTPHeaderDict) else 'Unknown'}")
-
-        except Exception as e:
-            raise ValueError(f"Unknown error occured: {e}")
+        order_page_result = self._openapi_service.order_api.orders_get(QueryModel(
+            page=PageInfo(index=1, size=amount),
+            filter=RootFilter(filters=[Filter(field="OrderName", operator="Contains", value=name)]),
+            sortCriteria=[SortCriterion(direction="Desc", propertyName="OrderDate")]
+            ))
 
         orders = [self.get_order_by_id(order.id) for order in order_page_result.items]
         return orders

{rapidata-2.24.1 → rapidata-2.24.3}/src/rapidata/rapidata_client/selection/static_selection.py

@@ -8,7 +8,7 @@ class StaticSelection(RapidataSelection):
     Given a list of RapidIds, theses specific rapids will be shown in order for every session.
     
     Args:
-        selections (list[str]): List of rapid ids to show.
+        rapid_ids (list[str]): List of rapid ids to show.
     """
 
     def __init__(self, rapid_ids: list[str]):

{rapidata-2.24.1 → rapidata-2.24.3}/src/rapidata/rapidata_client/validation/validation_set_manager.py

@@ -81,7 +81,7 @@ class ValidationSetManager:
             raise ValueError("The number of contexts and datapoints must be equal")
 
         if(explanations and len(explanations) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
        
         logger.debug("Creating classification rapids")
         rapids: list[Rapid] = []
@@ -149,7 +149,7 @@ class ValidationSetManager:
             raise ValueError("The number of contexts and datapoints must be equal")
  
         if(explanation and len(explanation) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
         
         logger.debug("Creating comparison rapids")
         rapids: list[Rapid] = []
@@ -213,7 +213,7 @@ class ValidationSetManager:
             raise ValueError("The number of datapoints, truths, and sentences must be equal")
  
         if(explanation and len(explanation) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
 
         logger.debug("Creating select words rapids")
         rapids: list[Rapid] = []
@@ -274,7 +274,7 @@ class ValidationSetManager:
             raise ValueError("The number of contexts and datapoints must be equal")
  
         if(explanation and len(explanation) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
         
         logger.debug("Creating locate rapids")
         rapids = []
@@ -335,7 +335,7 @@ class ValidationSetManager:
             raise ValueError("The number of contexts and datapoints must be equal")
  
         if(explanation and len(explanation) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
 
         logger.debug("Creating draw rapids")
         rapids: list[Rapid] = []
@@ -396,7 +396,7 @@ class ValidationSetManager:
             raise ValueError("The number of contexts and datapoints must be equal")
  
         if(explanation and len(explanation) != len(datapoints)):
-            raise ValueError("The numeber of reasons and datapoints must be equal, the index must align, but can be padded with None")
+            raise ValueError("The number of explanations and datapoints must be equal, the index must align, but can be padded with None")
               
         logger.debug("Creating timestamp rapids")
         rapids: list[Rapid] = []
@@ -475,10 +475,8 @@ class ValidationSetManager:
         Returns:
             RapidataValidationSet: The ValidationSet instance.
         """
-        try:
-            validation_set = self.__openapi_service.validation_api.validation_set_validation_set_id_get(validation_set_id=validation_set_id)
-        except Exception:
-            raise ValueError(f"ValidationSet with ID {validation_set_id} not found.")
+        
+        validation_set = self.__openapi_service.validation_api.validation_set_validation_set_id_get(validation_set_id=validation_set_id)
         
         return RapidataValidationSet(validation_set_id, str(validation_set.name), self.__openapi_service)
 
@@ -493,18 +491,12 @@ class ValidationSetManager:
         Returns:
             list[RapidataValidationSet]: The list of validation sets.
         """
-        try:
-            validation_page_result = self.__openapi_service.validation_api.validation_sets_get(QueryModel(
-                page=PageInfo(index=1, size=amount),
-                filter=RootFilter(filters=[Filter(field="Name", operator="Contains", value=name)]),
-                sortCriteria=[SortCriterion(direction="Desc", propertyName="CreatedAt")]
-                ))
-
-        except BadRequestException as e:
-            raise ValueError(f"Error occured during request. \nError: {e.body} \nTraceid: {e.headers.get('X-Trace-Id') if isinstance(e.headers, HTTPHeaderDict) else 'Unknown'}")
-
-        except Exception as e:
-            raise ValueError(f"Unknown error occured: {e}")
+
+        validation_page_result = self.__openapi_service.validation_api.validation_sets_get(QueryModel(
+            page=PageInfo(index=1, size=amount),
+            filter=RootFilter(filters=[Filter(field="Name", operator="Contains", value=name)]),
+            sortCriteria=[SortCriterion(direction="Desc", propertyName="CreatedAt")]
+            ))
 
         validation_sets = [self.get_validation_set_by_id(str(validation_set.id)) for validation_set in validation_page_result.items]
         return validation_sets