openparser-sdk 0.0.1__py3-none-any.whl

openparser/_generated/errors.py

@@ -0,0 +1,14 @@
+""" Contains shared errors types that can be raised from API functions """
+
+class UnexpectedStatus(Exception):
+    """Raised by api functions when the response status an undocumented status and Client.raise_on_unexpected_status is True"""
+
+    def __init__(self, status_code: int, content: bytes):
+        self.status_code = status_code
+        self.content = content
+
+        super().__init__(
+            f"Unexpected status code: {status_code}\n\nResponse content:\n{content.decode(errors='ignore')}"
+        )
+
+__all__ = ["UnexpectedStatus"]

openparser/_generated/models/__init__.py

@@ -0,0 +1,261 @@
+""" Contains all the data models used in inputs/outputs """
+
+from .batch_child_page import BatchChildPage
+from .batch_child_summary import BatchChildSummary
+from .batch_job_accepted import BatchJobAccepted
+from .batch_job_accepted_operation import BatchJobAcceptedOperation
+from .batch_summary_counts import BatchSummaryCounts
+from .bounding_box import BoundingBox
+from .chunk_provenance_span import ChunkProvenanceSpan
+from .content_kind import ContentKind
+from .create_extraction_pipeline_request import CreateExtractionPipelineRequest
+from .create_extraction_pipeline_request_grounding import CreateExtractionPipelineRequestGrounding
+from .create_extraction_pipeline_request_llm_options import CreateExtractionPipelineRequestLlmOptions
+from .create_extraction_pipeline_request_llm_options_reasoning_effort_type_1 import CreateExtractionPipelineRequestLlmOptionsReasoningEffortType1
+from .create_extraction_pipeline_request_ocr_options import CreateExtractionPipelineRequestOcrOptions
+from .create_extraction_pipeline_request_schema import CreateExtractionPipelineRequestSchema
+from .create_file_body import CreateFileBody
+from .delete_extraction_pipeline_response import DeleteExtractionPipelineResponse
+from .delete_file_response import DeleteFileResponse
+from .error_body import ErrorBody
+from .error_body_details import ErrorBodyDetails
+from .error_response import ErrorResponse
+from .extract_async_body import ExtractAsyncBody
+from .extract_batch_body import ExtractBatchBody
+from .extract_batch_item import ExtractBatchItem
+from .extract_batch_item_grounding import ExtractBatchItemGrounding
+from .extract_batch_item_llm_options import ExtractBatchItemLlmOptions
+from .extract_batch_item_llm_options_reasoning_effort_type_1 import ExtractBatchItemLlmOptionsReasoningEffortType1
+from .extract_batch_item_ocr_options import ExtractBatchItemOcrOptions
+from .extract_batch_item_schema import ExtractBatchItemSchema
+from .extract_batch_request import ExtractBatchRequest
+from .extract_batch_request_items_item import ExtractBatchRequestItemsItem
+from .extract_batch_request_items_item_grounding import ExtractBatchRequestItemsItemGrounding
+from .extract_batch_request_items_item_llm_options import ExtractBatchRequestItemsItemLlmOptions
+from .extract_batch_request_items_item_llm_options_reasoning_effort_type_1 import ExtractBatchRequestItemsItemLlmOptionsReasoningEffortType1
+from .extract_batch_request_items_item_ocr_options import ExtractBatchRequestItemsItemOcrOptions
+from .extract_batch_request_items_item_schema import ExtractBatchRequestItemsItemSchema
+from .extract_batch_request_output_format import ExtractBatchRequestOutputFormat
+from .extract_request import ExtractRequest
+from .extract_request_grounding import ExtractRequestGrounding
+from .extract_request_llm_options import ExtractRequestLlmOptions
+from .extract_request_llm_options_reasoning_effort_type_1 import ExtractRequestLlmOptionsReasoningEffortType1
+from .extract_request_ocr_options import ExtractRequestOcrOptions
+from .extract_request_output_format import ExtractRequestOutputFormat
+from .extract_request_schema import ExtractRequestSchema
+from .extract_sync_body import ExtractSyncBody
+from .extraction_attempt import ExtractionAttempt
+from .extraction_attempt_kind import ExtractionAttemptKind
+from .extraction_attempt_status import ExtractionAttemptStatus
+from .extraction_chunk import ExtractionChunk
+from .extraction_citation import ExtractionCitation
+from .extraction_citation_granularity import ExtractionCitationGranularity
+from .extraction_citation_source_type import ExtractionCitationSourceType
+from .extraction_grounding_field import ExtractionGroundingField
+from .extraction_grounding_mode import ExtractionGroundingMode
+from .extraction_grounding_result import ExtractionGroundingResult
+from .extraction_pipeline import ExtractionPipeline
+from .extraction_pipeline_list_response import ExtractionPipelineListResponse
+from .extraction_pipeline_llm_options import ExtractionPipelineLlmOptions
+from .extraction_pipeline_llm_options_reasoning_effort_type_0_type_1 import ExtractionPipelineLlmOptionsReasoningEffortType0Type1
+from .extraction_pipeline_ocr_options import ExtractionPipelineOcrOptions
+from .extraction_pipeline_schema import ExtractionPipelineSchema
+from .extraction_terminal_result import ExtractionTerminalResult
+from .extraction_terminal_result_reasoning_effort_type_0 import ExtractionTerminalResultReasoningEffortType0
+from .extraction_usage_totals import ExtractionUsageTotals
+from .job import Job
+from .job_accepted import JobAccepted
+from .job_accepted_operation import JobAcceptedOperation
+from .job_extraction_schema import JobExtractionSchema
+from .job_failure import JobFailure
+from .job_failure_details import JobFailureDetails
+from .job_list_response import JobListResponse
+from .job_operation import JobOperation
+from .job_progress import JobProgress
+from .job_related_extractions_item import JobRelatedExtractionsItem
+from .job_status import JobStatus
+from .job_summary import JobSummary
+from .json_schema_object import JsonSchemaObject
+from .list_llm_models_mode import ListLlmModelsMode
+from .ocr_llm_model_catalog_entry import OcrLlmModelCatalogEntry
+from .ocr_llm_model_catalog_entry_pricing import OcrLlmModelCatalogEntryPricing
+from .ocr_llm_model_catalog_entry_reasoning_type_0 import OcrLlmModelCatalogEntryReasoningType0
+from .ocr_llm_model_catalog_entry_reasoning_type_0_default_effort_type_0 import OcrLlmModelCatalogEntryReasoningType0DefaultEffortType0
+from .ocr_llm_model_catalog_entry_reasoning_type_0_supported_efforts_type_0_item import OcrLlmModelCatalogEntryReasoningType0SupportedEffortsType0Item
+from .ocr_llm_model_catalog_entry_recommendation import OcrLlmModelCatalogEntryRecommendation
+from .ocr_llm_models_response import OcrLlmModelsResponse
+from .ocr_llm_models_response_mode import OcrLlmModelsResponseMode
+from .ocr_model import OcrModel
+from .ocr_model_catalog_entry import OcrModelCatalogEntry
+from .ocr_model_catalog_entry_availability import OcrModelCatalogEntryAvailability
+from .ocr_model_catalog_entry_capabilities import OcrModelCatalogEntryCapabilities
+from .ocr_model_catalog_entry_capabilities_options import OcrModelCatalogEntryCapabilitiesOptions
+from .ocr_model_catalog_entry_option_defaults import OcrModelCatalogEntryOptionDefaults
+from .ocr_model_catalog_entry_pricing import OcrModelCatalogEntryPricing
+from .ocr_models_response import OcrModelsResponse
+from .ocr_output_format import OcrOutputFormat
+from .paddle_raw_profile import PaddleRawProfile
+from .paddle_raw_profile_options import PaddleRawProfileOptions
+from .page_block import PageBlock
+from .page_block_kind import PageBlockKind
+from .page_block_polygon_type_0_item import PageBlockPolygonType0Item
+from .parse_async_body import ParseAsyncBody
+from .parse_batch_body import ParseBatchBody
+from .parse_batch_item import ParseBatchItem
+from .parse_batch_item_ocr_options import ParseBatchItemOcrOptions
+from .parse_batch_request import ParseBatchRequest
+from .parse_batch_request_items_item import ParseBatchRequestItemsItem
+from .parse_batch_request_items_item_ocr_options import ParseBatchRequestItemsItemOcrOptions
+from .parse_batch_request_output_format import ParseBatchRequestOutputFormat
+from .parse_request import ParseRequest
+from .parse_request_ocr_options import ParseRequestOcrOptions
+from .parse_request_output_format import ParseRequestOutputFormat
+from .parse_sync_body import ParseSyncBody
+from .parsed_document import ParsedDocument
+from .public_file import PublicFile
+from .raw_parse_result import RawParseResult
+from .raw_parse_result_result import RawParseResultResult
+from .region import Region
+from .region_content import RegionContent
+from .region_polygon_type_0_item import RegionPolygonType0Item
+from .region_type import RegionType
+from .suggest_schema_request import SuggestSchemaRequest
+from .suggest_schema_response import SuggestSchemaResponse
+from .suggest_schema_response_schema import SuggestSchemaResponseSchema
+from .update_extraction_pipeline_request import UpdateExtractionPipelineRequest
+from .update_extraction_pipeline_request_grounding import UpdateExtractionPipelineRequestGrounding
+from .update_extraction_pipeline_request_llm_options_type_0 import UpdateExtractionPipelineRequestLlmOptionsType0
+from .update_extraction_pipeline_request_llm_options_type_0_reasoning_effort_type_1 import UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1
+from .update_extraction_pipeline_request_ocr_options_type_0 import UpdateExtractionPipelineRequestOcrOptionsType0
+from .update_extraction_pipeline_request_schema import UpdateExtractionPipelineRequestSchema
+
+__all__ = (
+    "BatchChildPage",
+    "BatchChildSummary",
+    "BatchJobAccepted",
+    "BatchJobAcceptedOperation",
+    "BatchSummaryCounts",
+    "BoundingBox",
+    "ChunkProvenanceSpan",
+    "ContentKind",
+    "CreateExtractionPipelineRequest",
+    "CreateExtractionPipelineRequestGrounding",
+    "CreateExtractionPipelineRequestLlmOptions",
+    "CreateExtractionPipelineRequestLlmOptionsReasoningEffortType1",
+    "CreateExtractionPipelineRequestOcrOptions",
+    "CreateExtractionPipelineRequestSchema",
+    "CreateFileBody",
+    "DeleteExtractionPipelineResponse",
+    "DeleteFileResponse",
+    "ErrorBody",
+    "ErrorBodyDetails",
+    "ErrorResponse",
+    "ExtractAsyncBody",
+    "ExtractBatchBody",
+    "ExtractBatchItem",
+    "ExtractBatchItemGrounding",
+    "ExtractBatchItemLlmOptions",
+    "ExtractBatchItemLlmOptionsReasoningEffortType1",
+    "ExtractBatchItemOcrOptions",
+    "ExtractBatchItemSchema",
+    "ExtractBatchRequest",
+    "ExtractBatchRequestItemsItem",
+    "ExtractBatchRequestItemsItemGrounding",
+    "ExtractBatchRequestItemsItemLlmOptions",
+    "ExtractBatchRequestItemsItemLlmOptionsReasoningEffortType1",
+    "ExtractBatchRequestItemsItemOcrOptions",
+    "ExtractBatchRequestItemsItemSchema",
+    "ExtractBatchRequestOutputFormat",
+    "ExtractionAttempt",
+    "ExtractionAttemptKind",
+    "ExtractionAttemptStatus",
+    "ExtractionChunk",
+    "ExtractionCitation",
+    "ExtractionCitationGranularity",
+    "ExtractionCitationSourceType",
+    "ExtractionGroundingField",
+    "ExtractionGroundingMode",
+    "ExtractionGroundingResult",
+    "ExtractionPipeline",
+    "ExtractionPipelineListResponse",
+    "ExtractionPipelineLlmOptions",
+    "ExtractionPipelineLlmOptionsReasoningEffortType0Type1",
+    "ExtractionPipelineOcrOptions",
+    "ExtractionPipelineSchema",
+    "ExtractionTerminalResult",
+    "ExtractionTerminalResultReasoningEffortType0",
+    "ExtractionUsageTotals",
+    "ExtractRequest",
+    "ExtractRequestGrounding",
+    "ExtractRequestLlmOptions",
+    "ExtractRequestLlmOptionsReasoningEffortType1",
+    "ExtractRequestOcrOptions",
+    "ExtractRequestOutputFormat",
+    "ExtractRequestSchema",
+    "ExtractSyncBody",
+    "Job",
+    "JobAccepted",
+    "JobAcceptedOperation",
+    "JobExtractionSchema",
+    "JobFailure",
+    "JobFailureDetails",
+    "JobListResponse",
+    "JobOperation",
+    "JobProgress",
+    "JobRelatedExtractionsItem",
+    "JobStatus",
+    "JobSummary",
+    "JsonSchemaObject",
+    "ListLlmModelsMode",
+    "OcrLlmModelCatalogEntry",
+    "OcrLlmModelCatalogEntryPricing",
+    "OcrLlmModelCatalogEntryReasoningType0",
+    "OcrLlmModelCatalogEntryReasoningType0DefaultEffortType0",
+    "OcrLlmModelCatalogEntryReasoningType0SupportedEffortsType0Item",
+    "OcrLlmModelCatalogEntryRecommendation",
+    "OcrLlmModelsResponse",
+    "OcrLlmModelsResponseMode",
+    "OcrModel",
+    "OcrModelCatalogEntry",
+    "OcrModelCatalogEntryAvailability",
+    "OcrModelCatalogEntryCapabilities",
+    "OcrModelCatalogEntryCapabilitiesOptions",
+    "OcrModelCatalogEntryOptionDefaults",
+    "OcrModelCatalogEntryPricing",
+    "OcrModelsResponse",
+    "OcrOutputFormat",
+    "PaddleRawProfile",
+    "PaddleRawProfileOptions",
+    "PageBlock",
+    "PageBlockKind",
+    "PageBlockPolygonType0Item",
+    "ParseAsyncBody",
+    "ParseBatchBody",
+    "ParseBatchItem",
+    "ParseBatchItemOcrOptions",
+    "ParseBatchRequest",
+    "ParseBatchRequestItemsItem",
+    "ParseBatchRequestItemsItemOcrOptions",
+    "ParseBatchRequestOutputFormat",
+    "ParsedDocument",
+    "ParseRequest",
+    "ParseRequestOcrOptions",
+    "ParseRequestOutputFormat",
+    "ParseSyncBody",
+    "PublicFile",
+    "RawParseResult",
+    "RawParseResultResult",
+    "Region",
+    "RegionContent",
+    "RegionPolygonType0Item",
+    "RegionType",
+    "SuggestSchemaRequest",
+    "SuggestSchemaResponse",
+    "SuggestSchemaResponseSchema",
+    "UpdateExtractionPipelineRequest",
+    "UpdateExtractionPipelineRequestGrounding",
+    "UpdateExtractionPipelineRequestLlmOptionsType0",
+    "UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1",
+    "UpdateExtractionPipelineRequestOcrOptionsType0",
+    "UpdateExtractionPipelineRequestSchema",
+)

openparser/_generated/models/batch_child_page.py

@@ -0,0 +1,97 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar, BinaryIO, TextIO, TYPE_CHECKING, Generator
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..types import UNSET, Unset
+
+from ..types import UNSET, Unset
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.batch_child_summary import BatchChildSummary
+
+
+
+
+
+T = TypeVar("T", bound="BatchChildPage")
+
+
+
+@_attrs_define
+class BatchChildPage:
+    """
+        Attributes:
+            items (list[BatchChildSummary]):
+            next_cursor (None | str | Unset): Present when more child summaries are available.
+     """
+
+    items: list[BatchChildSummary]
+    next_cursor: None | str | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.batch_child_summary import BatchChildSummary
+        items = []
+        for items_item_data in self.items:
+            items_item = items_item_data.to_dict()
+            items.append(items_item)
+
+
+
+        next_cursor: None | str | Unset
+        if isinstance(self.next_cursor, Unset):
+            next_cursor = UNSET
+        else:
+            next_cursor = self.next_cursor
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+            "items": items,
+        })
+        if next_cursor is not UNSET:
+            field_dict["next_cursor"] = next_cursor
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.batch_child_summary import BatchChildSummary
+        d = dict(src_dict)
+        items = []
+        _items = d.pop("items")
+        for items_item_data in (_items):
+            items_item = BatchChildSummary.from_dict(items_item_data)
+
+
+
+            items.append(items_item)
+
+
+        def _parse_next_cursor(data: object) -> None | str | Unset:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            return cast(None | str | Unset, data)
+
+        next_cursor = _parse_next_cursor(d.pop("next_cursor", UNSET))
+
+
+        batch_child_page = cls(
+            items=items,
+            next_cursor=next_cursor,
+        )
+
+        return batch_child_page

openparser/_generated/models/batch_child_summary.py

@@ -0,0 +1,195 @@
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any, TypeVar, BinaryIO, TextIO, TYPE_CHECKING, Generator
+
+from attrs import define as _attrs_define
+from attrs import field as _attrs_field
+
+from ..types import UNSET, Unset
+
+from ..models.job_status import JobStatus
+from ..models.ocr_output_format import OcrOutputFormat
+from ..types import UNSET, Unset
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.extraction_terminal_result import ExtractionTerminalResult
+  from ..models.job_failure import JobFailure
+  from ..models.parsed_document import ParsedDocument
+  from ..models.raw_parse_result import RawParseResult
+
+
+
+
+
+T = TypeVar("T", bound="BatchChildSummary")
+
+
+
+@_attrs_define
+class BatchChildSummary:
+    """
+        Attributes:
+            client_item_id (str):
+            job_id (str): Prefixed public id for an OCR job (`opj_…`). Example: opj_V1StGXR8_Z5jdHi6B-myT.
+            file_index (int):
+            status (JobStatus): Durable job status. For batch parent jobs, status is derived from children after each
+                child transition:
+                1. If any child is non-terminal, the parent remains `queued` only while every child is
+                   queued; it becomes `running` once any child is running or terminal.
+                2. When every child is terminal and any child is `indeterminate`, the parent is
+                   `indeterminate`.
+                3. When every child is terminal, none are `indeterminate`, and any child is `failed`:
+                   the parent is `failed` if zero children succeeded, otherwise `succeeded` (mixed
+                   success/failure closes as parent `succeeded` while preserving failed children in
+                   summaries).
+                4. When every child is `succeeded`, the parent is `succeeded`.
+
+                Partial failures are always retained on child summaries; parent status does not drop
+                failed children from results.
+            output_format (OcrOutputFormat):
+            error (JobFailure | Unset):
+            result (ExtractionTerminalResult | ParsedDocument | RawParseResult | Unset): Terminal child result when `status`
+                is `succeeded`.
+     """
+
+    client_item_id: str
+    job_id: str
+    file_index: int
+    status: JobStatus
+    output_format: OcrOutputFormat
+    error: JobFailure | Unset = UNSET
+    result: ExtractionTerminalResult | ParsedDocument | RawParseResult | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.extraction_terminal_result import ExtractionTerminalResult
+        from ..models.job_failure import JobFailure
+        from ..models.parsed_document import ParsedDocument
+        from ..models.raw_parse_result import RawParseResult
+        client_item_id = self.client_item_id
+
+        job_id = self.job_id
+
+        file_index = self.file_index
+
+        status = self.status.value
+
+        output_format = self.output_format.value
+
+        error: dict[str, Any] | Unset = UNSET
+        if not isinstance(self.error, Unset):
+            error = self.error.to_dict()
+
+        result: dict[str, Any] | Unset
+        if isinstance(self.result, Unset):
+            result = UNSET
+        elif isinstance(self.result, ParsedDocument):
+            result = self.result.to_dict()
+        elif isinstance(self.result, RawParseResult):
+            result = self.result.to_dict()
+        else:
+            result = self.result.to_dict()
+
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+            "client_item_id": client_item_id,
+            "job_id": job_id,
+            "file_index": file_index,
+            "status": status,
+            "output_format": output_format,
+        })
+        if error is not UNSET:
+            field_dict["error"] = error
+        if result is not UNSET:
+            field_dict["result"] = result
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.extraction_terminal_result import ExtractionTerminalResult
+        from ..models.job_failure import JobFailure
+        from ..models.parsed_document import ParsedDocument
+        from ..models.raw_parse_result import RawParseResult
+        d = dict(src_dict)
+        client_item_id = d.pop("client_item_id")
+
+        job_id = d.pop("job_id")
+
+        file_index = d.pop("file_index")
+
+        status = JobStatus(d.pop("status"))
+
+
+
+
+        output_format = OcrOutputFormat(d.pop("output_format"))
+
+
+
+
+        _error = d.pop("error", UNSET)
+        error: JobFailure | Unset
+        if isinstance(_error,  Unset):
+            error = UNSET
+        else:
+            error = JobFailure.from_dict(_error)
+
+
+
+
+        def _parse_result(data: object) -> ExtractionTerminalResult | ParsedDocument | RawParseResult | Unset:
+            if isinstance(data, Unset):
+                return data
+            try:
+                if not isinstance(data, dict):
+                    raise TypeError()
+                result_type_0 = ParsedDocument.from_dict(data)
+
+
+
+                return result_type_0
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            try:
+                if not isinstance(data, dict):
+                    raise TypeError()
+                result_type_1 = RawParseResult.from_dict(data)
+
+
+
+                return result_type_1
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            if not isinstance(data, dict):
+                raise TypeError()
+            result_type_2 = ExtractionTerminalResult.from_dict(data)
+
+
+
+            return result_type_2
+
+        result = _parse_result(d.pop("result", UNSET))
+
+
+        batch_child_summary = cls(
+            client_item_id=client_item_id,
+            job_id=job_id,
+            file_index=file_index,
+            status=status,
+            output_format=output_format,
+            error=error,
+            result=result,
+        )
+
+        return batch_child_summary