rapidata 0.1.3__py3-none-any.whl → 0.1.6__py3-none-any.whl

openapi/openapi-client/openapi_client/models/workflow_split_model_filter_configs_inner.py

@@ -0,0 +1,154 @@
+# 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 json
+import pprint
+from pydantic import BaseModel, ConfigDict, Field, StrictStr, ValidationError, field_validator
+from typing import Any, List, Optional
+from openapi_client.models.classification_metadata_filter_config import ClassificationMetadataFilterConfig
+from openapi_client.models.count_classification_metadata_filter_config import CountClassificationMetadataFilterConfig
+from openapi_client.models.location_metadata_exists_filter_config import LocationMetadataExistsFilterConfig
+from pydantic import StrictStr, Field
+from typing import Union, List, Set, Optional, Dict
+from typing_extensions import Literal, Self
+
+WORKFLOWSPLITMODELFILTERCONFIGSINNER_ONE_OF_SCHEMAS = ["ClassificationMetadataFilterConfig", "CountClassificationMetadataFilterConfig", "LocationMetadataExistsFilterConfig"]
+
+class WorkflowSplitModelFilterConfigsInner(BaseModel):
+    """
+    WorkflowSplitModelFilterConfigsInner
+    """
+    # data type: ClassificationMetadataFilterConfig
+    oneof_schema_1_validator: Optional[ClassificationMetadataFilterConfig] = None
+    # data type: CountClassificationMetadataFilterConfig
+    oneof_schema_2_validator: Optional[CountClassificationMetadataFilterConfig] = None
+    # data type: LocationMetadataExistsFilterConfig
+    oneof_schema_3_validator: Optional[LocationMetadataExistsFilterConfig] = None
+    actual_instance: Optional[Union[ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig]] = None
+    one_of_schemas: Set[str] = { "ClassificationMetadataFilterConfig", "CountClassificationMetadataFilterConfig", "LocationMetadataExistsFilterConfig" }
+
+    model_config = ConfigDict(
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    discriminator_value_class_map: Dict[str, str] = {
+    }
+
+    def __init__(self, *args, **kwargs) -> None:
+        if args:
+            if len(args) > 1:
+                raise ValueError("If a position argument is used, only 1 is allowed to set `actual_instance`")
+            if kwargs:
+                raise ValueError("If a position argument is used, keyword arguments cannot be used.")
+            super().__init__(actual_instance=args[0])
+        else:
+            super().__init__(**kwargs)
+
+    @field_validator('actual_instance')
+    def actual_instance_must_validate_oneof(cls, v):
+        instance = WorkflowSplitModelFilterConfigsInner.model_construct()
+        error_messages = []
+        match = 0
+        # validate data type: ClassificationMetadataFilterConfig
+        if not isinstance(v, ClassificationMetadataFilterConfig):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `ClassificationMetadataFilterConfig`")
+        else:
+            match += 1
+        # validate data type: CountClassificationMetadataFilterConfig
+        if not isinstance(v, CountClassificationMetadataFilterConfig):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `CountClassificationMetadataFilterConfig`")
+        else:
+            match += 1
+        # validate data type: LocationMetadataExistsFilterConfig
+        if not isinstance(v, LocationMetadataExistsFilterConfig):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `LocationMetadataExistsFilterConfig`")
+        else:
+            match += 1
+        if match > 1:
+            # more than 1 match
+            raise ValueError("Multiple matches found when setting `actual_instance` in WorkflowSplitModelFilterConfigsInner with oneOf schemas: ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig. Details: " + ", ".join(error_messages))
+        elif match == 0:
+            # no match
+            raise ValueError("No match found when setting `actual_instance` in WorkflowSplitModelFilterConfigsInner with oneOf schemas: ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig. Details: " + ", ".join(error_messages))
+        else:
+            return v
+
+    @classmethod
+    def from_dict(cls, obj: Union[str, Dict[str, Any]]) -> Self:
+        return cls.from_json(json.dumps(obj))
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Returns the object represented by the json string"""
+        instance = cls.model_construct()
+        error_messages = []
+        match = 0
+
+        # deserialize data into ClassificationMetadataFilterConfig
+        try:
+            instance.actual_instance = ClassificationMetadataFilterConfig.from_json(json_str)
+            match += 1
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # deserialize data into CountClassificationMetadataFilterConfig
+        try:
+            instance.actual_instance = CountClassificationMetadataFilterConfig.from_json(json_str)
+            match += 1
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # deserialize data into LocationMetadataExistsFilterConfig
+        try:
+            instance.actual_instance = LocationMetadataExistsFilterConfig.from_json(json_str)
+            match += 1
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+
+        if match > 1:
+            # more than 1 match
+            raise ValueError("Multiple matches found when deserializing the JSON string into WorkflowSplitModelFilterConfigsInner with oneOf schemas: ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig. Details: " + ", ".join(error_messages))
+        elif match == 0:
+            # no match
+            raise ValueError("No match found when deserializing the JSON string into WorkflowSplitModelFilterConfigsInner with oneOf schemas: ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig. Details: " + ", ".join(error_messages))
+        else:
+            return instance
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the actual instance"""
+        if self.actual_instance is None:
+            return "null"
+
+        if hasattr(self.actual_instance, "to_json") and callable(self.actual_instance.to_json):
+            return self.actual_instance.to_json()
+        else:
+            return json.dumps(self.actual_instance)
+
+    def to_dict(self) -> Optional[Union[Dict[str, Any], ClassificationMetadataFilterConfig, CountClassificationMetadataFilterConfig, LocationMetadataExistsFilterConfig]]:
+        """Returns the dict representation of the actual instance"""
+        if self.actual_instance is None:
+            return None
+
+        if hasattr(self.actual_instance, "to_dict") and callable(self.actual_instance.to_dict):
+            return self.actual_instance.to_dict()
+        else:
+            # primitive type
+            return self.actual_instance
+
+    def to_str(self) -> str:
+        """Returns the string representation of the actual instance"""
+        return pprint.pformat(self.model_dump())
+
+

openapi/openapi-client/openapi_client/rest.py

@@ -0,0 +1,257 @@
+# 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
+import ssl
+
+import urllib3
+
+from openapi_client.exceptions import ApiException, ApiValueError
+
+SUPPORTED_SOCKS_PROXIES = {"socks5", "socks5h", "socks4", "socks4a"}
+RESTResponseType = urllib3.HTTPResponse
+
+
+def is_socks_proxy_url(url):
+    if url is None:
+        return False
+    split_section = url.split("://")
+    if len(split_section) < 2:
+        return False
+    else:
+        return split_section[0].lower() in SUPPORTED_SOCKS_PROXIES
+
+
+class RESTResponse(io.IOBase):
+
+    def __init__(self, resp) -> None:
+        self.response = resp
+        self.status = resp.status
+        self.reason = resp.reason
+        self.data = None
+
+    def read(self):
+        if self.data is None:
+            self.data = self.response.data
+        return self.data
+
+    def getheaders(self):
+        """Returns a dictionary of the response headers."""
+        return self.response.headers
+
+    def getheader(self, name, default=None):
+        """Returns a given response header."""
+        return self.response.headers.get(name, default)
+
+
+class RESTClientObject:
+
+    def __init__(self, configuration) -> None:
+        # urllib3.PoolManager will pass all kw parameters to connectionpool
+        # https://github.com/shazow/urllib3/blob/f9409436f83aeb79fbaf090181cd81b784f1b8ce/urllib3/poolmanager.py#L75  # noqa: E501
+        # https://github.com/shazow/urllib3/blob/f9409436f83aeb79fbaf090181cd81b784f1b8ce/urllib3/connectionpool.py#L680  # noqa: E501
+        # Custom SSL certificates and client certificates: http://urllib3.readthedocs.io/en/latest/advanced-usage.html  # noqa: E501
+
+        # cert_reqs
+        if configuration.verify_ssl:
+            cert_reqs = ssl.CERT_REQUIRED
+        else:
+            cert_reqs = ssl.CERT_NONE
+
+        pool_args = {
+            "cert_reqs": cert_reqs,
+            "ca_certs": configuration.ssl_ca_cert,
+            "cert_file": configuration.cert_file,
+            "key_file": configuration.key_file,
+        }
+        if configuration.assert_hostname is not None:
+            pool_args['assert_hostname'] = (
+                configuration.assert_hostname
+            )
+
+        if configuration.retries is not None:
+            pool_args['retries'] = configuration.retries
+
+        if configuration.tls_server_name:
+            pool_args['server_hostname'] = configuration.tls_server_name
+
+
+        if configuration.socket_options is not None:
+            pool_args['socket_options'] = configuration.socket_options
+
+        if configuration.connection_pool_maxsize is not None:
+            pool_args['maxsize'] = configuration.connection_pool_maxsize
+
+        # https pool manager
+        self.pool_manager: urllib3.PoolManager
+
+        if configuration.proxy:
+            if is_socks_proxy_url(configuration.proxy):
+                from urllib3.contrib.socks import SOCKSProxyManager
+                pool_args["proxy_url"] = configuration.proxy
+                pool_args["headers"] = configuration.proxy_headers
+                self.pool_manager = SOCKSProxyManager(**pool_args)
+            else:
+                pool_args["proxy_url"] = configuration.proxy
+                pool_args["proxy_headers"] = configuration.proxy_headers
+                self.pool_manager = urllib3.ProxyManager(**pool_args)
+        else:
+            self.pool_manager = urllib3.PoolManager(**pool_args)
+
+    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 {}
+
+        timeout = None
+        if _request_timeout:
+            if isinstance(_request_timeout, (int, float)):
+                timeout = urllib3.Timeout(total=_request_timeout)
+            elif (
+                    isinstance(_request_timeout, tuple)
+                    and len(_request_timeout) == 2
+                ):
+                timeout = urllib3.Timeout(
+                    connect=_request_timeout[0],
+                    read=_request_timeout[1]
+                )
+
+        try:
+            # For `POST`, `PUT`, `PATCH`, `OPTIONS`, `DELETE`
+            if method in ['POST', 'PUT', 'PATCH', 'OPTIONS', 'DELETE']:
+
+                # no content type provided or payload is json
+                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 = self.pool_manager.request(
+                        method,
+                        url,
+                        body=request_body,
+                        timeout=timeout,
+                        headers=headers,
+                        preload_content=False
+                    )
+                elif content_type == 'application/x-www-form-urlencoded':
+                    r = self.pool_manager.request(
+                        method,
+                        url,
+                        fields=post_params,
+                        encode_multipart=False,
+                        timeout=timeout,
+                        headers=headers,
+                        preload_content=False
+                    )
+                elif content_type == 'multipart/form-data':
+                    # must del headers['Content-Type'], or the correct
+                    # Content-Type which generated by urllib3 will be
+                    # overwritten.
+                    del headers['Content-Type']
+                    # Ensures that dict objects are serialized
+                    post_params = [(a, json.dumps(b)) if isinstance(b, dict) else (a,b) for a, b in post_params]
+                    r = self.pool_manager.request(
+                        method,
+                        url,
+                        fields=post_params,
+                        encode_multipart=True,
+                        timeout=timeout,
+                        headers=headers,
+                        preload_content=False
+                    )
+                # Pass a `string` parameter directly in the body to support
+                # other content types than JSON when `body` argument is
+                # provided in serialized form.
+                elif isinstance(body, str) or isinstance(body, bytes):
+                    r = self.pool_manager.request(
+                        method,
+                        url,
+                        body=body,
+                        timeout=timeout,
+                        headers=headers,
+                        preload_content=False
+                    )
+                elif headers['Content-Type'] == 'text/plain' and isinstance(body, bool):
+                    request_body = "true" if body else "false"
+                    r = self.pool_manager.request(
+                        method,
+                        url,
+                        body=request_body,
+                        preload_content=False,
+                        timeout=timeout,
+                        headers=headers)
+                else:
+                    # Cannot generate the request from given parameters
+                    msg = """Cannot prepare a request message for provided
+                             arguments. Please check that your arguments match
+                             declared content type."""
+                    raise ApiException(status=0, reason=msg)
+            # For `GET`, `HEAD`
+            else:
+                r = self.pool_manager.request(
+                    method,
+                    url,
+                    fields={},
+                    timeout=timeout,
+                    headers=headers,
+                    preload_content=False
+                )
+        except urllib3.exceptions.SSLError as e:
+            msg = "\n".join([type(e).__name__, str(e)])
+            raise ApiException(status=0, reason=msg)
+
+        return RESTResponse(r)

rapidata/rapidata_client/{workflow/feature_flags → feature_flags}/feature_flags.py

@@ -1,10 +1,12 @@
+from openapi_client.models.feature_flag_model import FeatureFlagModel
+
+
 class FeatureFlags:
     def __init__(self):
         self._flags: dict[str, str] = {}
 
-    def to_list(self) -> list[dict[str, str]]:
-        # transform dict of flags to list of flags
-        return [{"key": name, "value": value} for name, value in self._flags.items()]
+    def to_list(self) -> list[FeatureFlagModel]:
+        return [FeatureFlagModel(key=name, value=value) for name, value in self._flags.items()]
     
     def alert_on_fast_response(self, value: int):
         self._flags["alertOnFastResponse"] = str(value)

rapidata/rapidata_client/metadata/base_metadata.py

@@ -0,0 +1,12 @@
+from abc import abstractmethod
+from typing import Any
+
+
+class Metadata:
+
+    def __init__(self):
+        pass
+
+    @abstractmethod
+    def to_model(self) -> Any:
+        pass

rapidata/rapidata_client/metadata/transcription_metadata.py

@@ -0,0 +1,19 @@
+from openapi_client.models.transcription_metadata_input import (
+    TranscriptionMetadataInput,
+)
+from rapidata.rapidata_client.metadata.base_metadata import Metadata
+
+
+class TranscriptionMetadata(Metadata):
+
+    def __init__(self, transcription: str, identifier: str = "transcription"):
+        super().__init__()
+        self.identifier = identifier
+        self.transcription = transcription
+
+    def to_model(self):
+        return TranscriptionMetadataInput(
+            _t="TranscriptionMetadataInput",
+            identifier=self.identifier,
+            transcription=self.transcription,
+        )

rapidata/rapidata_client/order/dataset/rapidata_dataset.py

@@ -1,26 +1,52 @@
+from itertools import zip_longest
 import os
+from typing import List
+
+from openapi_client.models.datapoint_metadata_model import DatapointMetadataModel
+from openapi_client.models.datapoint_metadata_model_metadata_inner import (
+    DatapointMetadataModelMetadataInner,
+)
+from openapi_client.models.upload_text_sources_to_dataset_model import (
+    UploadTextSourcesToDatasetModel,
+)
+from rapidata.rapidata_client.metadata.base_metadata import Metadata
 from rapidata.service import LocalFileService
-from rapidata.service import RapidataService
+from rapidata.service.openapi_service import OpenAPIService
 
 
 class RapidataDataset:
 
-    def __init__(self, dataset_id: str, rapidata_service: RapidataService):
+    def __init__(self, dataset_id: str, openapi_service: OpenAPIService):
         self.dataset_id = dataset_id
-        self.rapidata_service = rapidata_service
+        self.openapi_service = openapi_service
         self.local_file_service = LocalFileService()
 
     def add_texts(self, texts: list[str]):
-        self.rapidata_service.dataset.upload_text_sources(self.dataset_id, texts)
-
-    def add_images_from_paths(self, image_paths: list[str]):
-        image_names = [os.path.basename(image_path) for image_path in image_paths]
-        images = self.local_file_service.load_images(image_paths)
-
-        self.rapidata_service.dataset.upload_images(self.dataset_id, images, image_names)
-
-    def add_videos_from_paths(self, video_paths: list[str]):
-        video_names = [os.path.basename(video_path) for video_path in video_paths]
-        videos = self.local_file_service.load_videos(video_paths)
-
-        self.rapidata_service.dataset.upload_videos(self.dataset_id, videos, video_names)
+        model = UploadTextSourcesToDatasetModel(
+            datasetId=self.dataset_id, textSources=texts
+        )
+        self.openapi_service.dataset_api.dataset_upload_text_sources_to_dataset_post(
+            model
+        )
+
+    def add_media_from_paths(
+        self,
+        image_paths: list[str],
+        metadata: List[Metadata] | None = None,
+    ):
+        if metadata is not None and len(metadata) != len(image_paths):
+            raise ValueError(
+                "metadata must be None or have the same length as image_paths"
+            )
+
+        for image_path, meta in zip_longest(image_paths, metadata or []):
+            if not os.path.exists(image_path):
+                raise FileNotFoundError(f"File not found: {image_path}")
+            
+            meta_model = meta.to_model() if meta else None
+            model = DatapointMetadataModel(
+                datasetId=self.dataset_id,
+                metadata=[DatapointMetadataModelMetadataInner(meta_model)] if meta_model else [],
+            )
+
+            self.openapi_service.dataset_api.dataset_create_datapoint_post(model=model, files=[image_path])  # type: ignore