rapidata 2.11.0__tar.gz → 2.11.1__tar.gz

{rapidata-2.11.0 → rapidata-2.11.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rapidata
-Version: 2.11.0
+Version: 2.11.1
 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-2.11.0 → rapidata-2.11.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rapidata"
-version = "2.11.0"
+version = "2.11.1"
 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-2.11.0 → rapidata-2.11.1}/src/rapidata/rapidata_client/assets/_media_asset.py

@@ -78,7 +78,7 @@ class MediaAsset(BaseAsset):
         
         self._url = None
         self._content = None
-        self._session: None | requests.Session  = None
+        self.session: None | requests.Session  = None
         
         if re.match(r'^https?://', path):
             self._url = path
@@ -238,11 +238,11 @@ class MediaAsset(BaseAsset):
             requests.exceptions.RequestException: If download fails after all retries
         """
         # Use existing session or throw error if not set
-        if self._session is None:
+        if self.session is None:
             raise RuntimeError("HTTP session not configured")
 
         try:
-            response = self._session.get(
+            response = self.session.get(
                 url, 
                 stream=False,
                 timeout=(5, 30)  # (connect timeout, read timeout)

{rapidata-2.11.0 → rapidata-2.11.1}/src/rapidata/rapidata_client/order/_rapidata_dataset.py

@@ -136,14 +136,14 @@ class RapidataDataset:
             try:
                 # Get identifier for this upload (URL or file path)
                 if isinstance(media_asset, MediaAsset):
-                    media_asset._session = session
+                    media_asset.session = session
                     assets = [media_asset]
                     identifier = media_asset._url if media_asset._url else media_asset.path
                     identifiers_to_track = [identifier] if identifier else []
                 elif isinstance(media_asset, MultiAsset):
                     assets = cast(list[MediaAsset], media_asset.assets)
                     for asset in assets:
-                        asset._session = session
+                        asset.session = session
                     identifiers_to_track: list[str] = [
                         (asset._url if asset._url else cast(str, asset.path)) 
                         for asset in assets

{rapidata-2.11.0 → rapidata-2.11.1}/src/rapidata/rapidata_client/validation/rapidata_validation_set.py

@@ -1,5 +1,7 @@
 from rapidata.rapidata_client.validation.rapids.rapids import Rapid
 from rapidata.service.openapi_service import OpenAPIService
+from requests.adapters import HTTPAdapter, Retry
+import requests
 
 class RapidataValidationSet:
     """A class for interacting with a Rapidata validation set.
@@ -17,6 +19,7 @@ class RapidataValidationSet:
         self.id = validation_set_id
         self.name = name
         self.__openapi_service = openapi_service
+        self.__session = self._get_session()
     
     def add_rapid(self, rapid: Rapid):
         """Add a Rapid to the validation set.
@@ -24,7 +27,37 @@ class RapidataValidationSet:
         Args:
             rapid (Rapid): The Rapid to add to the validation set.
         """
-        rapid._add_to_validation_set(self.id, self.__openapi_service)
+        rapid._add_to_validation_set(self.id, self.__openapi_service, self.__session)
+
+    def _get_session(self, max_retries: int = 5, max_workers: int = 10) -> requests.Session:   
+        """Get a requests session with retry logic.
+
+
+        Args:
+            max_retries (int): The maximum number of retries.
+            max_workers (int): The maximum number of workers.
+
+        Returns:
+            requests.Session: A requests session with retry logic.
+        """
+        session = requests.Session()
+        retries = Retry(
+            total=max_retries,
+            backoff_factor=1,
+            status_forcelist=[500, 502, 503, 504],
+            allowed_methods=["GET"],
+            respect_retry_after_header=True
+        )
+
+        adapter = HTTPAdapter(
+            pool_connections=max_workers * 2,
+            pool_maxsize=max_workers * 4,
+            max_retries=retries
+        )
+        session.mount('http://', adapter)
+        session.mount('https://', adapter)
+
+        return session
 
     def __str__(self):
         return f"name: '{self.name}' id: {self.id}"

{rapidata-2.11.0 → rapidata-2.11.1}/src/rapidata/rapidata_client/validation/rapids/rapids.py

@@ -22,6 +22,8 @@ from rapidata.api_client.models.datapoint_metadata_model_metadata_inner import (
 
 from rapidata.service.openapi_service import OpenAPIService
 
+import requests
+
 class Rapid():
     def __init__(self, asset: MediaAsset | TextAsset | MultiAsset, metadata: Sequence[Metadata], payload: Any, truth: Any, randomCorrectProbability: float, explanation: str | None):
         self.asset = asset
@@ -31,14 +33,14 @@ class Rapid():
         self.randomCorrectProbability = randomCorrectProbability
         self.explanation = explanation 
 
-    def _add_to_validation_set(self, validationSetId: str, openapi_service: OpenAPIService):
+    def _add_to_validation_set(self, validationSetId: str, openapi_service: OpenAPIService, session: requests.Session) -> None:
         if isinstance(self.asset, TextAsset) or (isinstance(self.asset, MultiAsset) and isinstance(self.asset.assets[0], TextAsset)):
             openapi_service.validation_api.validation_add_validation_text_rapid_post(
                 add_validation_text_rapid_model=self.__to_text_model(validationSetId)
             )
 
         elif isinstance(self.asset, MediaAsset) or (isinstance(self.asset, MultiAsset) and isinstance(self.asset.assets[0], MediaAsset)):
-            model = self.__to_media_model(validationSetId)
+            model = self.__to_media_model(validationSetId, session=session)
             openapi_service.validation_api.validation_add_validation_rapid_post(
                 model=model[0], files=model[1]
             )
@@ -46,7 +48,7 @@ class Rapid():
         else:
             raise TypeError("The asset must be a MediaAsset, TextAsset, or MultiAsset")
 
-    def __to_media_model(self, validationSetId: str) -> tuple[AddValidationRapidModel, list[StrictStr | tuple[StrictStr, StrictBytes] | StrictBytes]]:
+    def __to_media_model(self, validationSetId: str, session: requests.Session) -> tuple[AddValidationRapidModel, list[StrictStr | tuple[StrictStr, StrictBytes] | StrictBytes]]:
         assets: list[MediaAsset] = [] 
         if isinstance(self.asset, MultiAsset):
             for asset in self.asset.assets:
@@ -61,6 +63,9 @@ class Rapid():
         if isinstance(self.asset, MediaAsset):
             assets = [self.asset]
 
+        for asset in assets:
+            asset.session = session
+
         return (AddValidationRapidModel(
             validationSetId=validationSetId,
             payload=AddValidationRapidModelPayload(self.payload),