rapidata 2.17.0__tar.gz → 2.18.0__tar.gz

{rapidata-2.17.0 → rapidata-2.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rapidata
-Version: 2.17.0
+Version: 2.18.0
 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
@@ -12,6 +12,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: authlib (>=1.5.1,<2.0.0)
 Requires-Dist: colorama (==0.4.6)
 Requires-Dist: deprecated (>=1.2.14,<2.0.0)
 Requires-Dist: pandas (>=2.2.3,<3.0.0)

{rapidata-2.17.0 → rapidata-2.18.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rapidata"
-version = "2.17.0"
+version = "2.18.0"
 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"
@@ -19,6 +19,7 @@ deprecated = "^1.2.14"
 colorama = "0.4.6"
 tinytag = "^2.0.0"
 pandas = "^2.2.3"
+authlib = "^1.5.1"
 
 [tool.poetry.group.dev.dependencies]
 python-dotenv = "^1.0.1"

rapidata-2.18.0/src/rapidata/api_client/rest.py

@@ -0,0 +1,231 @@
+# 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
+
+import io
+import json
+import re
+from typing import Dict, Optional
+
+import requests
+from authlib.integrations.requests_client import OAuth2Session
+from requests.adapters import HTTPAdapter
+from urllib3 import Retry
+
+from rapidata.api_client.exceptions import ApiException, ApiValueError
+
+
+class RESTResponse(io.IOBase):
+
+    def __init__(self, resp: requests.Response) -> None:
+        self.response = resp
+        self.status = resp.status_code
+        self.reason = resp.reason
+        self.data = None
+
+    def read(self):
+        if self.data is None:
+            self.data = self.response.content
+        return self.data
+
+    def getheaders(self) -> Dict[str, str]:
+        """Returns a dictionary of the response headers."""
+        return dict(self.response.headers)
+
+    def getheader(self, name, default=None) -> Optional[str]:
+        """Returns a given response header."""
+        return self.response.headers.get(name, default)
+
+
+RESTResponseType = RESTResponse
+
+
+class RESTClientObject:
+
+    def __init__(self, configuration) -> None:
+        self.configuration = configuration
+
+        self.session: Optional[OAuth2Session] = None
+
+    def setup_oauth_client_credentials(
+            self, client_id: str, client_secret: str, token_endpoint: str, scope: str
+    ):
+        self.session = OAuth2Session(
+            client_id=client_id,
+            client_secret=client_secret,
+            token_endpoint=token_endpoint,
+            scope=scope,
+        )
+        self._configure_session_defaults()
+        self.session.fetch_token()
+
+    def setup_oauth_with_token(self,
+                               client_id: str | None,
+                               client_secret: str | None,
+                               token: dict,
+                               token_endpoint: str,
+                               leeway: int = 60):
+        self.session = OAuth2Session(
+            token=token,
+            token_endpoint=token_endpoint,
+            client_id=client_id,
+            client_secret=client_secret,
+            leeway=leeway,
+        )
+        self._configure_session_defaults()
+
+    def request(
+            self,
+            method,
+            url,
+            headers=None,
+            body=None,
+            post_params=None,
+            _request_timeout=None,
+    ):
+        """Perform requests.
+
+        :param method: http request method
+        :param url: http request url
+        :param headers: http request headers
+        :param body: request json body, for `application/json`
+        :param post_params: request post parameters,
+                            `application/x-www-form-urlencoded`
+                            and `multipart/form-data`
+        :param _request_timeout: timeout setting for this request. If one
+                                 number provided, it will be total request
+                                 timeout. It can also be a pair (tuple) of
+                                 (connection, read) timeouts.
+        """
+        method = method.upper()
+        assert method in ["GET", "HEAD", "DELETE", "POST", "PUT", "PATCH", "OPTIONS"]
+
+        if post_params and body:
+            raise ApiValueError(
+                "body parameter cannot be used with post_params parameter."
+            )
+
+        post_params = post_params or {}
+        headers = headers or {}
+
+        if not self.session:
+            raise ApiValueError(
+                "OAuth2 session is not initialized. Please initialize it before making requests."
+            )
+
+        session = self.session
+
+        timeout = None
+        if _request_timeout:
+            if isinstance(_request_timeout, (int, float)):
+                timeout = _request_timeout
+            elif isinstance(_request_timeout, tuple) and len(_request_timeout) == 2:
+                timeout = _request_timeout
+
+        try:
+            if method in ["POST", "PUT", "PATCH", "OPTIONS", "DELETE"]:
+                content_type = headers.get("Content-Type")
+
+                if not content_type or re.search("json", content_type, re.IGNORECASE):
+                    request_body = None
+                    if body is not None:
+                        request_body = json.dumps(body)
+                    r = session.request(method, url, data=request_body, timeout=timeout, headers=headers)
+
+                elif content_type == 'application/x-www-form-urlencoded':
+                    r = session.request(method, url, data=post_params, timeout=timeout, headers=headers)
+
+                elif content_type == 'multipart/form-data':
+                    del headers['Content-Type']
+                    files = []
+                    data = {}
+
+                    for key, value in post_params:
+                        if isinstance(value, tuple) and len(value) >= 2:
+                            # This is a file tuple (filename, file_data, [content_type])
+                            filename, file_data = value[0], value[1]
+                            content_type = value[2] if len(value) > 2 else None
+                            files.append((key, (filename, file_data, content_type)))
+                        elif isinstance(value, dict):
+                            # JSON-serialize dictionary values
+                            if key in data:
+                                # If we already have this key, handle as needed
+                                # (convert to list or append to existing list)
+                                if not isinstance(data[key], list):
+                                    data[key] = [data[key]]
+                                data[key].append(json.dumps(value))
+                            else:
+                                data[key] = json.dumps(value)
+                        else:
+                            # Regular form data
+                            if key in data:
+                                if not isinstance(data[key], list):
+                                    data[key] = [data[key]]
+                                data[key].append(value)
+                            else:
+                                data[key] = value
+                    r = session.request(method, url, files=files, data=data, timeout=timeout, headers=headers)
+
+                elif isinstance(body, str) or isinstance(body, bytes):
+                    r = session.request(method, url, data=body, timeout=timeout, headers=headers)
+
+                elif headers['Content-Type'].startswith('text/') and isinstance(body, bool):
+                    request_body = 'true' if body else 'false'
+                    r = session.request(method, url, data=request_body, timeout=timeout, headers=headers)
+
+                else:
+                    msg = '''Cannot prepare a request message for provided arguments.
+                             Please check that your arguments match declared content type.'''
+                    raise ApiException(status=0, reason=msg)
+
+            else:
+                r = session.request(method, url, params={}, timeout=timeout, headers=headers)
+
+        except requests.exceptions.SSLError as e:
+            msg = '\n'.join([type(e).__name__, str(e)])
+            raise ApiException(status=0, reason=msg)
+
+        return RESTResponse(r)
+
+    def _configure_session_defaults(self):
+        self.session.verify = (
+            self.configuration.ssl_ca_cert
+            if self.configuration.ssl_ca_cert
+            else self.configuration.verify_ssl
+        )
+
+        if self.configuration.cert_file and self.configuration.key_file:
+            self.session.cert = (
+                self.configuration.cert_file,
+                self.configuration.key_file,
+            )
+
+        if self.configuration.retries is not None:
+            retry = Retry(
+                total=self.configuration.retries,
+                backoff_factor=0.3,
+                status_forcelist=[429, 500, 502, 503, 504],
+            )
+            adapter = HTTPAdapter(max_retries=retry)
+            self.session.mount("https://", adapter)
+            # noinspection HttpUrlsUsage
+            self.session.mount("http://", adapter)
+
+        if self.configuration.proxy:
+            self.session.proxies = {
+                "http": self.configuration.proxy,
+                "https": self.configuration.proxy,
+            }
+
+            if self.configuration.proxy_headers:
+                for key, value in self.configuration.proxy_headers.items():
+                    self.session.headers[key] = value

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/order/rapidata_order.py

@@ -51,7 +51,7 @@ class RapidataOrder:
         """Runs the order to start collecting responses."""
         self.__openapi_service.order_api.order_submit_post(self.order_id)
         if print_link:
-            print(f"Order '{self.name}' is now viewable under: https://app.{self.__openapi_service.enviroment}/order/detail/{self.order_id}")
+            print(f"Order '{self.name}' is now viewable under: https://app.{self.__openapi_service.environment}/order/detail/{self.order_id}")
         return self
 
     def pause(self) -> None:
@@ -167,7 +167,7 @@ class RapidataOrder:
             Exception: If the order is not in processing state.
         """        
         campaign_id = self.__get_campaign_id()
-        auth_url = f"https://app.{self.__openapi_service.enviroment}/order/detail/{self.order_id}/preview?campaignId={campaign_id}"
+        auth_url = f"https://app.{self.__openapi_service.environment}/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="%/:=&?~#+!$,;'@()*[]")

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/rapidata_client.py

@@ -2,28 +2,37 @@ from rapidata.service.openapi_service import OpenAPIService
 
 from rapidata.rapidata_client.order.rapidata_order_manager import RapidataOrderManager
 
-from rapidata.rapidata_client.validation.validation_set_manager import ValidationSetManager
+from rapidata.rapidata_client.validation.validation_set_manager import (
+    ValidationSetManager,
+)
 
 from rapidata.rapidata_client.demographic.demographic_manager import DemographicManager
 
+
 class RapidataClient:
     """The Rapidata client is the main entry point for interacting with the Rapidata API. It allows you to create orders and validation sets."""
-    
+
     def __init__(
-        self,
-        client_id: str | None = None,
-        client_secret: str | None = None,
-        enviroment: str = "rapidata.ai",
-        oauth_scope: str = "openid",
-        cert_path: str | None = None,
+            self,
+            client_id: str | None = None,
+            client_secret: str | None = None,
+            environment: str = "rapidata.ai",
+            oauth_scope: str = "openid",
+            cert_path: str | None = None,
+            token: dict | None = None,
+            leeway: int = 60
     ):
-        """Initialize the RapidataClient. If both the client_id and client_secret are None, it will try using your credentials under "~/.config/rapidata/credentials.json". 
-        If this is not successful, it will open a browser windown and ask you to log in, then save your new credentials in said json file.
+        """Initialize the RapidataClient. If both the client_id and client_secret are None, it will try using your credentials under "~/.config/rapidata/credentials.json".
+        If this is not successful, it will open a browser window and ask you to log in, then save your new credentials in said json file.
 
         Args:
             client_id (str): The client ID for authentication.
             client_secret (str): The client secret for authentication.
-            enviroment (str, optional): The API endpoint.
+            environment (str, optional): The API endpoint.
+            oauth_scope (str, optional): The scopes to use for authentication. In general this does not need to be changed.
+            cert_path (str, optional): An optional path to a certificate file useful for development.
+            token (dict, optional): If you already have a token that the client should use for authentication. Important, if set, this needs to be the complete token object containing the access token, token type and expiration time.
+            leeway (int, optional): An optional leeway to use to determine if a token is expired. Defaults to 60 seconds.
 
         Attributes:
             order (RapidataOrderManager): The RapidataOrderManager instance.
@@ -32,17 +41,19 @@ class RapidataClient:
         self._openapi_service = OpenAPIService(
             client_id=client_id,
             client_secret=client_secret,
-            enviroment=enviroment,
+            environment=environment,
             oauth_scope=oauth_scope,
-            cert_path=cert_path
+            cert_path=cert_path,
+            token=token,
+            leeway=leeway,
         )
-        
+
         self.order = RapidataOrderManager(openapi_service=self._openapi_service)
-        
+
         self.validation = ValidationSetManager(openapi_service=self._openapi_service)
 
         self._demographic = DemographicManager(openapi_service=self._openapi_service)
 
     def reset_credentials(self):
-        """Reset the credentials saved in the configuration file for the current enviroment."""
+        """Reset the credentials saved in the configuration file for the current environment."""
         self._openapi_service.reset_credentials()

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/selection/__init__.py

@@ -5,3 +5,5 @@ from .validation_selection import ValidationSelection
 from .conditional_validation_selection import ConditionalValidationSelection
 from .capped_selection import CappedSelection
 from .shuffling_selection import ShufflingSelection
+from .ab_test_selection import AbTestSelection
+from .static_selection import StaticSelection

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/selection/ab_test_selection.py

@@ -20,7 +20,7 @@ class AbTestSelection(RapidataSelection):
         b_selections (Sequence[RapidataSelection]): List of selections for group B.
     """
 
-    def __init__(self, a_selections: Sequence[RapidataSelection], b_selections: Sequence[RapidataSelection], max_rapids: int):
+    def __init__(self, a_selections: Sequence[RapidataSelection], b_selections: Sequence[RapidataSelection]):
         self.a_selections = a_selections
         self.b_selections = b_selections
 

rapidata-2.18.0/src/rapidata/rapidata_client/selection/static_selection.py

@@ -0,0 +1,22 @@
+
+from rapidata.api_client.models.static_selection import StaticSelection as StaticSelectionModel
+from rapidata.rapidata_client.selection._base_selection import RapidataSelection
+
+class StaticSelection(RapidataSelection):
+    """StaticSelection Class
+
+    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.
+    """
+
+    def __init__(self, rapid_ids: list[str]):
+        self.rapid_ids = rapid_ids
+
+    def _to_model(self) -> StaticSelectionModel:
+        return StaticSelectionModel(
+            _t="StaticSelection",
+            rapidIds=self.rapid_ids
+        )
+    

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/validation/rapidata_validation_set.py

@@ -31,13 +31,13 @@ class RapidataValidationSet:
         rapid._add_to_validation_set(self.id, self.__openapi_service, self.__session)
         return self
 
-    def update_dimensions(self, dimensions: list[str] | None):
+    def update_dimensions(self, dimensions: list[str]):
         """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)
+        self.__openapi_service.validation_api.validation_validation_set_id_dimensions_patch(self.id, UpdateDimensionsModel(dimensions=dimensions))
         return self
 
     def _get_session(self, max_retries: int = 5, max_workers: int = 10) -> requests.Session:   

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/rapidata_client/validation/validation_set_manager.py

@@ -39,7 +39,7 @@ class ValidationSetManager:
         data_type: str = RapidataDataTypes.MEDIA,
         contexts: list[str] | None = None,
         explanations: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a classification validation set.
@@ -59,7 +59,7 @@ class ValidationSetManager:
                 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.
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -107,7 +107,7 @@ class ValidationSetManager:
         data_type: str = RapidataDataTypes.MEDIA,
         contexts: list[str] | None = None,
         explanation: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a comparison validation set.
@@ -127,7 +127,7 @@ class ValidationSetManager:
                 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.
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -175,7 +175,7 @@ class ValidationSetManager:
         required_precision: float = 1.0,
         required_completeness: float = 1.0,
         explanation: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a select words validation set.
@@ -194,7 +194,7 @@ class ValidationSetManager:
             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).
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -238,7 +238,7 @@ class ValidationSetManager:
         datapoints: list[str],
         contexts: list[str] | None = None,
         explanation: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a locate validation set.
@@ -253,7 +253,7 @@ class ValidationSetManager:
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -299,7 +299,7 @@ class ValidationSetManager:
         datapoints: list[str],
         contexts: list[str] | None = None,
         explanation: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a draw validation set.
@@ -314,7 +314,7 @@ class ValidationSetManager:
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -359,7 +359,7 @@ class ValidationSetManager:
         datapoints: list[str],
         contexts: list[str] | None = None,
         explanation: list[str | None] | None = None,
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True,
     ) -> RapidataValidationSet:
         """Create a timestamp validation set.
@@ -375,7 +375,7 @@ class ValidationSetManager:
             datapoints (list[str]): The datapoints that will be used for validation.
             contexts (list[str], optional): The contexts for each datapoint. Defaults to None.
             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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
 
         Example:
@@ -416,7 +416,7 @@ class ValidationSetManager:
     def create_mixed_set(self,
         name: str,
         rapids: list[Rapid],
-        dimensions: list[str] | None = None,
+        dimensions: list[str] = [],
         print_confirmation: bool = True
     ) -> RapidataValidationSet:
         """Create a validation set with a list of rapids.
@@ -424,7 +424,7 @@ 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.
+            dimensions (list[str], optional): The dimensions to add to the validation set accross which users will be tracked. Defaults to [] which is the default dimension.
             print_confirmation (bool, optional): Whether to print a confirmation message that validation set has been created. Defaults to True.
         """
 
@@ -468,10 +468,12 @@ class ValidationSetManager:
         if print_confirmation:
             print()
             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}",
+                  f"Now viewable under: https://app.{self.__openapi_service.environment}/validation-set/detail/{validation_set_id}",
                   sep="")
         
-        validation_set.update_dimensions(dimensions)
+        if dimensions:
+            validation_set.update_dimensions(dimensions)
+        
         return validation_set
 
 

{rapidata-2.17.0 → rapidata-2.18.0}/src/rapidata/service/credential_manager.py

@@ -133,9 +133,9 @@ class CredentialManager:
                 return credential
 
         return self._create_new_credentials()
-    
+
     def reset_credentials(self) -> None:
-        """Reset the stored credentials for current enviroment."""
+        """Reset the stored credentials for current environment."""
         credentials = self._read_credentials()
         if self.endpoint in credentials:
             del credentials[self.endpoint]