retab 0.0.69__py3-none-any.whl → 0.0.70__py3-none-any.whl

retab/resources/extractions/client.py

@@ -1,9 +1,11 @@
 import json
+from datetime import datetime
 from typing import Any, Dict, List, Literal
 
 from ..._resource import AsyncAPIResource, SyncAPIResource
 from ...types.standards import PreparedRequest
-from ...types.pagination import PaginatedList
+from ...types.pagination import PaginatedList, PaginationOrder
+from ...types.extractions.types import HumanReviewStatus
 
 class ExtractionsMixin:
     def prepare_list(
@@ -11,12 +13,12 @@ class ExtractionsMixin:
         before: str | None = None,
         after: str | None = None,
         limit: int = 10,
-        order: Literal["asc", "desc"] = "desc",
+        order: PaginationOrder = "desc",
         origin_dot_type: str | None = None,
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None, 
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         **extra_params: Any,
     ) -> PreparedRequest:
@@ -28,8 +30,8 @@ class ExtractionsMixin:
             "order": order,
             "origin_dot_type": origin_dot_type,
             "origin_dot_id": origin_dot_id,
-            "from_date": from_date,
-            "to_date": to_date,
+            "from_date": from_date.isoformat() if from_date else None,
+            "to_date": to_date.isoformat() if to_date else None,
             "human_review_status": human_review_status,
             # Note: metadata must be JSON-serialized as the backend expects a JSON string
             "metadata": json.dumps(metadata) if metadata else None,
@@ -40,34 +42,13 @@ class ExtractionsMixin:
         params = {k: v for k, v in params.items() if v is not None}
         return PreparedRequest(method="GET", url="/v1/extractions", params=params)
 
-    def prepare_count(
-        self,
-        origin_dot_type: str | None = None,
-        origin_dot_id: str | None = None,
-        human_review_status: str | None = "review_required",
-        metadata: Dict[str, str] | None = None,
-        **extra_params: Any,
-    ) -> PreparedRequest:
-        """Prepare a request to count extractions."""
-        params = {
-            "origin_dot_type": origin_dot_type,
-            "origin_dot_id": origin_dot_id,
-            "human_review_status": human_review_status,
-            # Note: metadata must be JSON-serialized as the backend expects a JSON string
-            "metadata": json.dumps(metadata) if metadata else None,
-        }
-        if extra_params:
-            params.update(extra_params)
-        params = {k: v for k, v in params.items() if v is not None}
-        return PreparedRequest(method="GET", url="/v1/extractions/count", params=params)
-
     def prepare_download(
         self,
         order: Literal["asc", "desc"] = "desc",
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         format: Literal["jsonl", "csv", "xlsx"] = "jsonl",
         **extra_params: Any,
@@ -76,8 +57,8 @@ class ExtractionsMixin:
         params = {
             "order": order,
             "origin_dot_id": origin_dot_id,
-            "from_date": from_date,
-            "to_date": to_date,
+            "from_date": from_date.isoformat() if from_date else None,
+            "to_date": to_date.isoformat() if to_date else None,
             "human_review_status": human_review_status,
             # Note: metadata must be JSON-serialized as the backend expects a JSON string
             "metadata": json.dumps(metadata) if metadata else None,
@@ -88,36 +69,11 @@ class ExtractionsMixin:
         params = {k: v for k, v in params.items() if v is not None}
         return PreparedRequest(method="GET", url="/v1/extractions/download", params=params)
 
-    def prepare_get_payload_for_export(
-        self,
-        project_id: str,
-        extraction_ids: List[str],
-        json_schema: dict[str, Any],
-        delimiter: str = ";",
-        line_delimiter: str = "\n",
-        quote: str = '"',
-        **extra_body: Any,
-    ) -> PreparedRequest:
-        """Prepare a request to export extractions as CSV."""
-        data = {
-            "project_id": project_id,
-            "extraction_ids": extraction_ids,
-            "json_schema": json_schema,
-        }
-        if extra_body:
-            data.update(extra_body)
-        params = {
-            "delimiter": delimiter,
-            "line_delimiter": line_delimiter,
-            "quote": quote,
-        }
-        return PreparedRequest(method="POST", url="/v1/extractions/get_payload_for_export", data=data, params=params)
-
     def prepare_update(
         self,
         extraction_id: str,
         predictions: dict[str, Any] | None = None,
-        human_review_status: str | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         json_schema: dict[str, Any] | None = None,
         inference_settings: dict[str, Any] | None = None,
         **extra_body: Any,
@@ -140,14 +96,9 @@ class ExtractionsMixin:
         """Prepare a request to get an extraction by ID."""
         return PreparedRequest(method="GET", url=f"/v1/extractions/{extraction_id}")
 
-    def prepare_get_distinct_field_values(self) -> PreparedRequest:
-        """Prepare a request to get distinct field values."""
-        return PreparedRequest(method="GET", url="/v1/extractions/fields")
-
-    def prepare_download_sample_document(self, extraction_id: str) -> PreparedRequest:
-        """Prepare a request to download the sample document for an extraction."""
-        return PreparedRequest(method="GET", url=f"/v1/extractions/{extraction_id}/sample-document")
-
+    def prepare_delete(self, extraction_id: str) -> PreparedRequest:
+        """Prepare a request to delete an extraction by ID."""
+        return PreparedRequest(method="DELETE", url=f"/v1/extractions/{extraction_id}")
 
 class Extractions(SyncAPIResource, ExtractionsMixin):
     """Extractions API wrapper"""
@@ -160,12 +111,12 @@ class Extractions(SyncAPIResource, ExtractionsMixin):
         before: str | None = None,
         after: str | None = None,
         limit: int = 10,
-        order: Literal["asc", "desc"] = "desc",
+        order: PaginationOrder = "desc",
         origin_dot_type: str | None = None,
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         **extra_params: Any,
     ) -> PaginatedList:
@@ -186,31 +137,14 @@ class Extractions(SyncAPIResource, ExtractionsMixin):
         response = self._client._prepared_request(request)
         return PaginatedList(**response)
 
-    def count(
-        self,
-        origin_dot_type: str | None = None,
-        origin_dot_id: str | None = None,
-        human_review_status: str | None = "review_required",
-        metadata: Dict[str, str] | None = None,
-        **extra_params: Any,
-    ) -> dict[str, int]:
-        """Count extractions matching filters."""
-        request = self.prepare_count(
-            origin_dot_type=origin_dot_type,
-            origin_dot_id=origin_dot_id,
-            human_review_status=human_review_status,
-            metadata=metadata,
-            **extra_params,
-        )
-        return self._client._prepared_request(request)
-
+    
     def download(
         self,
         order: Literal["asc", "desc"] = "desc",
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         format: Literal["jsonl", "csv", "xlsx"] = "jsonl",
         **extra_params: Any,
@@ -228,33 +162,12 @@ class Extractions(SyncAPIResource, ExtractionsMixin):
         )
         return self._client._prepared_request(request)
 
-    def get_payload_for_export(
-        self,
-        project_id: str,
-        extraction_ids: List[str],
-        json_schema: dict[str, Any],
-        delimiter: str = ";",
-        line_delimiter: str = "\n",
-        quote: str = '"',
-        **extra_body: Any,
-    ) -> dict[str, Any]:
-        """Export extractions as CSV. Returns csv_data, rows, and columns."""
-        request = self.prepare_get_payload_for_export(
-            project_id=project_id,
-            extraction_ids=extraction_ids,
-            json_schema=json_schema,
-            delimiter=delimiter,
-            line_delimiter=line_delimiter,
-            quote=quote,
-            **extra_body,
-        )
-        return self._client._prepared_request(request)
-
+   
     def update(
         self,
         extraction_id: str,
         predictions: dict[str, Any] | None = None,
-        human_review_status: str | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         json_schema: dict[str, Any] | None = None,
         inference_settings: dict[str, Any] | None = None,
         **extra_body: Any,
@@ -276,15 +189,10 @@ class Extractions(SyncAPIResource, ExtractionsMixin):
         request = self.prepare_get(extraction_id)
         return self._client._prepared_request(request)
 
-    def get_distinct_field_values(self) -> dict[str, List[str]]:
-        """Get distinct values for filterable fields."""
-        request = self.prepare_get_distinct_field_values()
-        return self._client._prepared_request(request)
-
-    def download_sample_document(self, extraction_id: str) -> bytes:
-        """Download the sample document for an extraction."""
-        request = self.prepare_download_sample_document(extraction_id)
-        return self._client._prepared_request(request)
+    def delete(self, extraction_id: str) -> None:
+        """Delete an extraction by ID."""
+        request = self.prepare_delete(extraction_id)
+        self._client._prepared_request(request)
 
 
 class AsyncExtractions(AsyncAPIResource, ExtractionsMixin):
@@ -298,12 +206,12 @@ class AsyncExtractions(AsyncAPIResource, ExtractionsMixin):
         before: str | None = None,
         after: str | None = None,
         limit: int = 10,
-        order: Literal["asc", "desc"] = "desc",
+        order: PaginationOrder = "desc",
         origin_dot_type: str | None = None,
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         **extra_params: Any,
     ) -> PaginatedList:
@@ -324,31 +232,13 @@ class AsyncExtractions(AsyncAPIResource, ExtractionsMixin):
         response = await self._client._prepared_request(request)
         return PaginatedList(**response)
 
-    async def count(
-        self,
-        origin_dot_type: str | None = None,
-        origin_dot_id: str | None = None,
-        human_review_status: str | None = "review_required",
-        metadata: Dict[str, str] | None = None,
-        **extra_params: Any,
-    ) -> dict[str, int]:
-        """Count extractions matching filters."""
-        request = self.prepare_count(
-            origin_dot_type=origin_dot_type,
-            origin_dot_id=origin_dot_id,
-            human_review_status=human_review_status,
-            metadata=metadata,
-            **extra_params,
-        )
-        return await self._client._prepared_request(request)
-
     async def download(
         self,
         order: Literal["asc", "desc"] = "desc",
         origin_dot_id: str | None = None,
-        from_date: str | None = None,
-        to_date: str | None = None,
-        human_review_status: str | None = None,
+        from_date: datetime | None = None,
+        to_date: datetime | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         metadata: Dict[str, str] | None = None,
         format: Literal["jsonl", "csv", "xlsx"] = "jsonl",
         **extra_params: Any,
@@ -366,33 +256,11 @@ class AsyncExtractions(AsyncAPIResource, ExtractionsMixin):
         )
         return await self._client._prepared_request(request)
 
-    async def get_payload_for_export(
-        self,
-        project_id: str,
-        extraction_ids: List[str],
-        json_schema: dict[str, Any],
-        delimiter: str = ";",
-        line_delimiter: str = "\n",
-        quote: str = '"',
-        **extra_body: Any,
-    ) -> dict[str, Any]:
-        """Export extractions as CSV. Returns csv_data, rows, and columns."""
-        request = self.prepare_get_payload_for_export(
-            project_id=project_id,
-            extraction_ids=extraction_ids,
-            json_schema=json_schema,
-            delimiter=delimiter,
-            line_delimiter=line_delimiter,
-            quote=quote,
-            **extra_body,
-        )
-        return await self._client._prepared_request(request)
-
     async def update(
         self,
         extraction_id: str,
         predictions: dict[str, Any] | None = None,
-        human_review_status: str | None = None,
+        human_review_status: HumanReviewStatus | None = None,
         json_schema: dict[str, Any] | None = None,
         inference_settings: dict[str, Any] | None = None,
         **extra_body: Any,
@@ -414,12 +282,7 @@ class AsyncExtractions(AsyncAPIResource, ExtractionsMixin):
         request = self.prepare_get(extraction_id)
         return await self._client._prepared_request(request)
 
-    async def get_distinct_field_values(self) -> dict[str, List[str]]:
-        """Get distinct values for filterable fields."""
-        request = self.prepare_get_distinct_field_values()
-        return await self._client._prepared_request(request)
-
-    async def download_sample_document(self, extraction_id: str) -> bytes:
-        """Download the sample document for an extraction."""
-        request = self.prepare_download_sample_document(extraction_id)
-        return await self._client._prepared_request(request)
+    async def delete(self, extraction_id: str) -> None:
+        """Delete an extraction by ID."""
+        request = self.prepare_delete(extraction_id)
+        await self._client._prepared_request(request)

retab/types/extractions/types.py

@@ -0,0 +1,3 @@
+from typing import Literal
+
+type HumanReviewStatus = Literal["success", "review_required", "reviewed"]

retab/types/pagination.py

@@ -1,4 +1,4 @@
-from typing import Any, List
+from typing import Any, List, Literal
 from pydantic import BaseModel
 
 
@@ -10,3 +10,5 @@ class ListMetadata(BaseModel):
 class PaginatedList(BaseModel):
     data: List[Any]
     list_metadata: ListMetadata
+
+type PaginationOrder = Literal["asc", "desc"]

{retab-0.0.69.dist-info → retab-0.0.70.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: retab
-Version: 0.0.69
+Version: 0.0.70
 Summary: Retab official python library
 Home-page: https://github.com/retab-dev/retab
 Author: Retab

{retab-0.0.69.dist-info → retab-0.0.70.dist-info}/RECORD

@@ -9,7 +9,7 @@ retab/resources/schemas.py,sha256=rZ6OzfmoYv-mGaRVzvXjO09dD-KxP74mZhOO8sMgcDQ,46
 retab/resources/documents/__init__.py,sha256=OjXmngFN0RKqO4SI-mJBNzr6Ex6rMxfq0DxaqzP0RQs,89
 retab/resources/documents/client.py,sha256=H-ylTrFcaC36iVj5XSWbwJB489n3GEWwbqsPgQQ50G4,31980
 retab/resources/extractions/__init__.py,sha256=2H1ezUG8hI5SmTRy6NFzXdYLOdGFFsFrI60uzkitV20,97
-retab/resources/extractions/client.py,sha256=EKjwSWGunOs2htDLnIrQxffrs9h_GJ99SChpS7xF8Is,15957
+retab/resources/extractions/client.py,sha256=sEoNjOgX91FTOgoJUV-I1A9A9xl1ciCdPlhYwjhEjbA,11035
 retab/resources/projects/__init__.py,sha256=tPR3_3tr7bsoYd618qmGjnYN2R23PmF5oCFd7Z5_HGY,85
 retab/resources/projects/client.py,sha256=nvqsDiVyeRrXsoYddwyXNmpZxaBLYWAGO2e0n6qkCzY,14988
 retab/types/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -17,13 +17,15 @@ retab/types/chat.py,sha256=x9VbtPMa4w6Gc0HrFC3ILl6cCnfEn5ytDnwJtZmlcys,1436
 retab/types/inference_settings.py,sha256=e4NDZHFdtrqi30Za1z0JhRU5PBO94yKxUGoK7S2kA3M,1053
 retab/types/mime.py,sha256=3Zk7vIbV8o4uJQiclVH-ncKKhs_ZeVi-UQV68TTu7s0,10039
 retab/types/modality.py,sha256=4B8LctdUBZVgIjtS2FjrJpljn2Eyse0XE1bpFsGb9O4,131
-retab/types/pagination.py,sha256=192h7raZ9RX8vUjipvvd71YbKVVDcCaqPJs564ESmqk,224
+retab/types/pagination.py,sha256=A0Fw06baPTfEaYwo3kvNs4vaupzlqylBc6tQH-2DFuY,279
 retab/types/standards.py,sha256=7aGtuvzzkKidvqY8JB2Cjfn43V80FeKwrTtp162kjKc,1477
 retab/types/documents/__init__.py,sha256=RaD6PnvRJw7QEVTh_PYNX6gckpLcxUJH7FKaopRKJzY,114
 retab/types/documents/correct_orientation.py,sha256=e-ivsslI6L6Gl0YkcslXw_DH620xMGEYVp4tdeviXeM,261
 retab/types/documents/create_messages.py,sha256=Cox0QgIyLhTXIvw1Nzd2BCnB9-5KAYgw_gads5eTaDw,7272
 retab/types/documents/extract.py,sha256=Z-Qsj5-lmWb9dkgyTTt3Z7Lpd4_7SZdRGErtV_aw8oE,16492
 retab/types/documents/parse.py,sha256=Jd6i-1UXhAtgntRBZItEHGHeevyLdLmbTQa1-HNrico,1305
+retab/types/extractions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+retab/types/extractions/types.py,sha256=mnCYSfJoEKsXN2eG-PrahnnQyR6RDjP5VO9sHC1Opmg,102
 retab/types/projects/__init__.py,sha256=I7P_dems5_LOLgYQ-4Bzt9B6P6jRlQwP-D_9GxRDhVk,155
 retab/types/projects/metrics.py,sha256=J8aZdVbqlszfxosAZyTB7l6lp9WgdL5QgLMlLrckN7k,1946
 retab/types/projects/model.py,sha256=f5NSIvwQQXhax4gHu57CE0pUkU_5S8t3aSfzAAqFFlI,4615
@@ -42,7 +44,7 @@ retab/utils/mime.py,sha256=mTP_lqSPttOP5DYJxopiWaeFXrUCPjhwd7y53nCVGO4,6189
 retab/utils/stream_context_managers.py,sha256=gI1gVQSj3nWz6Mvjz7Ix5AiY0g6vSL-c2tPfuP04izo,2314
 retab/utils/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 retab/utils/usage/json_schema.py,sha256=kRbL5E5OStlhlNlBXlxHNwaVHKd6MVhyqIb0y4aj8JA,84322
-retab-0.0.69.dist-info/METADATA,sha256=QM9e1Vs2hf34ROo3MutyMds_4zUekGqPYsN-8VU25EE,4532
-retab-0.0.69.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-retab-0.0.69.dist-info/top_level.txt,sha256=waQR0EGdhLIQtztoE3AXg7ik5ONQ9q_bsKVpyFuJdq0,6
-retab-0.0.69.dist-info/RECORD,,
+retab-0.0.70.dist-info/METADATA,sha256=fmovHmnRSdICMGaxGo7aOrYiOXbqyMmXBxUiG7gtdEQ,4532
+retab-0.0.70.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+retab-0.0.70.dist-info/top_level.txt,sha256=waQR0EGdhLIQtztoE3AXg7ik5ONQ9q_bsKVpyFuJdq0,6
+retab-0.0.70.dist-info/RECORD,,