clerk-sdk 0.5.8__tar.gz → 0.5.10__tar.gz

{clerk_sdk-0.5.8 → clerk_sdk-0.5.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: clerk-sdk
-Version: 0.5.8
+Version: 0.5.10
 Summary: Library for interacting with Clerk
 Project-URL: Homepage, https://github.com/F-ONE-Group/clerk_pypi
 Author-email: F-One <contact@f-one.group>

{clerk_sdk-0.5.8 → clerk_sdk-0.5.10}/clerk/__init__.py

@@ -1,4 +1,4 @@
 from .client import Clerk
 
 
-__version__ = "0.5.8"
+__version__ = "0.5.10"

{clerk_sdk-0.5.8 → clerk_sdk-0.5.10}/clerk/client.py

@@ -2,6 +2,7 @@ from typing import Any, Dict, List, Literal
 
 from clerk.base import BaseClerk
 from clerk.models.document import Document, GetDocumentsRequest, UploadDocumentRequest
+from clerk.models.prevalidation import FileClassificationResponse
 from .models.file import ParsedFile, UploadFile
 
 
@@ -70,74 +71,23 @@ class Clerk(BaseClerk):
         files_data = [f.to_multipart_format() for f in files]
         self.post_request(endpoint, params=params, files=files_data)
 
-
-class ClerkDocument(BaseClerk):
-    endpoint: str = "/document"
-
-    def upload_document(self, request: UploadDocumentRequest) -> Document:
-        endpoint = "/document"
+    def prevalidate_file(
+        self, project_id: str, workflow_id: str, file: UploadFile
+    ) -> Dict[str, Any]:
+        """Submit a prevalidation for a specific file. Returns the id for fetching the results later."""
+        endpoint = f"/prevalidation/file"
+        files_data = [file.to_multipart_format()]
         res = self.post_request(
-            endpoint=endpoint, data=request.data, files=request.files_
+            endpoint,
+            files=files_data,
+            data={"project_id": project_id, "workflow_id": workflow_id},
         )
-        return Document(**res.data[0])
-
-    def reprocess_document(self, document_id: str, workflow_id: str) -> Document:
-        endpoint = f"/document/{document_id}/reprocess"
-        res = self.put_request(endpoint=endpoint, data={"workflow_id": workflow_id})
-        return Document(**res.data[0])
-
-    def cancel_document_run(self, document_id: str) -> Document:
-        endpoint = f"/document/{document_id}/cancel"
-        res = self.post_request(endpoint=endpoint)
-        return Document(**res.data[0])
-
-    def update_document_structured_data(
-        self, document_id: str, updated_structured_data: Dict[str, Any]
-    ) -> Document:
-        endpoint = f"/document/{document_id}"
-        payload = dict(structured_data=updated_structured_data)
-        res = self.put_request(endpoint, json=payload)
-
-        return Document(**res.data[0])
-
-    def get_document(self, document_id: str) -> Document:
-        endpoint = f"/document/{document_id}"
-        res = self.get_request(endpoint=endpoint)
-        return Document(**res.data[0])
-
-    def get_documents(self, request: GetDocumentsRequest) -> List[Document]:
-        if not any(
-            [
-                request.organization_id,
-                request.project_id,
-                request.start_date,
-                request.end_date,
-                request.query,
-                request.include_statuses,
-            ]
-        ):
-            raise ValueError(
-                "At least one query parameter (organization_id, project_id, start_date, end_date, query, or include_statuses) must be provided."
-            )
-
-        endpoint = f"/documents"
-        params = request.model_dump(mode="json")
-        res = self.get_request(endpoint, params=params)
-
-        return [Document(**d) for d in res.data]
-
-    def get_files_document(self, document_id: str) -> List[ParsedFile]:
-        endpoint = f"/document/{document_id}/files"
-        res = self.get_request(endpoint=endpoint)
-        return [ParsedFile(**d) for d in res.data]
-
-    def add_files_to_document(
-        self,
-        document_id: str,
-        type: Literal["input", "output"],
-        files: List[UploadFile],
-    ):
-        endpoint = f"/document/{document_id}/files/upload"
-        params = {"type": type}
-        files_data = [f.to_multipart_format() for f in files]
-        self.post_request(endpoint, params=params, files=files_data)
+        return res.data[0]
+
+    def get_prevalidation_results(
+        self, workflow_run_id: str
+    ) -> FileClassificationResponse:
+        """Fetch the results of a previously submitted prevalidation."""
+        endpoint = f"/prevalidation/file"
+        res = self.get_request(endpoint, params={"workflow_run_id": workflow_run_id})
+        return FileClassificationResponse(**res.data[0])

clerk_sdk-0.5.10/clerk/models/prevalidation.py

@@ -0,0 +1,33 @@
+from typing import Dict, List, Optional
+from pydantic import BaseModel, Field
+
+
+class LabelWithDescriptions(BaseModel):
+    label: str = Field(..., description="The label/category name")
+    description: Optional[str] = Field(
+        None, description="Optional description of the label/category"
+    )
+    attributes: Optional[List[str]] = Field(
+        None, description="Optional attributes for the label/category"
+    )
+    start_page: Optional[int] = Field(
+        None, description="Start page for classification (0-based, inclusive)"
+    )
+    end_page: Optional[int] = Field(
+        None, description="End page for classification (0-based, exclusive)"
+    )
+
+
+class FileClassificationResponse(BaseModel):
+    valid: bool = Field(False, description="Whether the file classification is valid")
+    filename: str = Field(..., description="The name of the file that was classified")
+    classification: Optional[str] = Field(
+        None, description="The selected classification category"
+    )
+    reason: Optional[str] = Field(
+        None,
+        description="The reasoning behind the classification. To be filled if no classification is made.",
+    )
+    possible_categories: Optional[Dict[str, LabelWithDescriptions]] = Field(
+        None, description="Possible categories for classification"
+    )

{clerk_sdk-0.5.8 → clerk_sdk-0.5.10}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "clerk-sdk"
-version = "0.5.8"
+version = "0.5.10"
 description = "Library for interacting with Clerk"
 readme = "README.md"
 authors = [

{clerk_sdk-0.5.8 → clerk_sdk-0.5.10}/setup.py

@@ -13,7 +13,7 @@ gui_requirements = get_requirements("./clerk/gui_automation")
 
 setup(
     name="clerk-sdk",
-    version="0.5.8",
+    version="0.5.10",
     description="Library for interacting with Clerk",
     long_description=open("README.md").read(),
     long_description_content_type="text/markdown",