openparser-sdk 0.0.1__py3-none-any.whl

openparser/_generated/models/extract_request.py

@@ -0,0 +1,226 @@
+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.extract_request_grounding import ExtractRequestGrounding
+from ..models.extract_request_output_format import ExtractRequestOutputFormat
+from ..types import UNSET, Unset
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.extract_request_llm_options import ExtractRequestLlmOptions
+  from ..models.extract_request_ocr_options import ExtractRequestOcrOptions
+  from ..models.extract_request_schema import ExtractRequestSchema
+
+
+
+
+
+T = TypeVar("T", bound="ExtractRequest")
+
+
+
+@_attrs_define
+class ExtractRequest:
+    """ Single extract config. Provide either `pipeline_id` or inline extraction config.
+    The source is exactly one of multipart file bytes, `file_id`, or tenant-owned succeeded
+    `parse_job_id`. Parse reuse is single-extract-only, forbids `ocr_model` / `ocr_options`,
+    does not run OCR, and adds no page charge. `parse_job_id` is part of idempotency identity.
+
+        Attributes:
+            pipeline_id (str | Unset): Saved extraction pipeline id (`oppl_…`). Inline extraction fields are forbidden.
+                Admission records pipeline id/version provenance and snapshots the effective extraction
+                configuration; the worker never re-reads the pipeline. With `parse_job_id`, source-parse
+                provenance is recorded separately and the pipeline's OCR settings are not executed.
+            ocr_model (str | Unset):
+            ocr_options (ExtractRequestOcrOptions | Unset):
+            llm_model (str | Unset):
+            llm_options (ExtractRequestLlmOptions | Unset):
+            schema (ExtractRequestSchema | Unset):
+            repair_attempts (int | Unset):
+            grounding (ExtractRequestGrounding | Unset): Optional field grounding mode. Defaults to `none` for inline
+                requests. Changing
+                grounding with the same Idempotency-Key returns `409 idempotency_conflict`.
+                Unsupported schemas return `422 grounding_unsupported_schema`.
+            file_id (str | Unset):
+            parse_job_id (str | Unset): Tenant-owned succeeded `parse` job (`opj_…`) whose canonical `openparser@1`
+                ParsedDocument
+                is reused. Mutually exclusive with multipart bytes and `file_id`; forbidden in batch.
+            output_format (ExtractRequestOutputFormat | Unset):  Default: ExtractRequestOutputFormat.OPENPARSER1.
+     """
+
+    pipeline_id: str | Unset = UNSET
+    ocr_model: str | Unset = UNSET
+    ocr_options: ExtractRequestOcrOptions | Unset = UNSET
+    llm_model: str | Unset = UNSET
+    llm_options: ExtractRequestLlmOptions | Unset = UNSET
+    schema: ExtractRequestSchema | Unset = UNSET
+    repair_attempts: int | Unset = UNSET
+    grounding: ExtractRequestGrounding | Unset = UNSET
+    file_id: str | Unset = UNSET
+    parse_job_id: str | Unset = UNSET
+    output_format: ExtractRequestOutputFormat | Unset = ExtractRequestOutputFormat.OPENPARSER1
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.extract_request_llm_options import ExtractRequestLlmOptions
+        from ..models.extract_request_ocr_options import ExtractRequestOcrOptions
+        from ..models.extract_request_schema import ExtractRequestSchema
+        pipeline_id = self.pipeline_id
+
+        ocr_model = self.ocr_model
+
+        ocr_options: dict[str, Any] | Unset = UNSET
+        if not isinstance(self.ocr_options, Unset):
+            ocr_options = self.ocr_options.to_dict()
+
+        llm_model = self.llm_model
+
+        llm_options: dict[str, Any] | Unset = UNSET
+        if not isinstance(self.llm_options, Unset):
+            llm_options = self.llm_options.to_dict()
+
+        schema: dict[str, Any] | Unset = UNSET
+        if not isinstance(self.schema, Unset):
+            schema = self.schema.to_dict()
+
+        repair_attempts = self.repair_attempts
+
+        grounding: str | Unset = UNSET
+        if not isinstance(self.grounding, Unset):
+            grounding = self.grounding.value
+
+
+        file_id = self.file_id
+
+        parse_job_id = self.parse_job_id
+
+        output_format: str | Unset = UNSET
+        if not isinstance(self.output_format, Unset):
+            output_format = self.output_format.value
+
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+        })
+        if pipeline_id is not UNSET:
+            field_dict["pipeline_id"] = pipeline_id
+        if ocr_model is not UNSET:
+            field_dict["ocr_model"] = ocr_model
+        if ocr_options is not UNSET:
+            field_dict["ocr_options"] = ocr_options
+        if llm_model is not UNSET:
+            field_dict["llm_model"] = llm_model
+        if llm_options is not UNSET:
+            field_dict["llm_options"] = llm_options
+        if schema is not UNSET:
+            field_dict["schema"] = schema
+        if repair_attempts is not UNSET:
+            field_dict["repair_attempts"] = repair_attempts
+        if grounding is not UNSET:
+            field_dict["grounding"] = grounding
+        if file_id is not UNSET:
+            field_dict["file_id"] = file_id
+        if parse_job_id is not UNSET:
+            field_dict["parse_job_id"] = parse_job_id
+        if output_format is not UNSET:
+            field_dict["output_format"] = output_format
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.extract_request_llm_options import ExtractRequestLlmOptions
+        from ..models.extract_request_ocr_options import ExtractRequestOcrOptions
+        from ..models.extract_request_schema import ExtractRequestSchema
+        d = dict(src_dict)
+        pipeline_id = d.pop("pipeline_id", UNSET)
+
+        ocr_model = d.pop("ocr_model", UNSET)
+
+        _ocr_options = d.pop("ocr_options", UNSET)
+        ocr_options: ExtractRequestOcrOptions | Unset
+        if isinstance(_ocr_options,  Unset):
+            ocr_options = UNSET
+        else:
+            ocr_options = ExtractRequestOcrOptions.from_dict(_ocr_options)
+
+
+
+
+        llm_model = d.pop("llm_model", UNSET)
+
+        _llm_options = d.pop("llm_options", UNSET)
+        llm_options: ExtractRequestLlmOptions | Unset
+        if isinstance(_llm_options,  Unset):
+            llm_options = UNSET
+        else:
+            llm_options = ExtractRequestLlmOptions.from_dict(_llm_options)
+
+
+
+
+        _schema = d.pop("schema", UNSET)
+        schema: ExtractRequestSchema | Unset
+        if isinstance(_schema,  Unset):
+            schema = UNSET
+        else:
+            schema = ExtractRequestSchema.from_dict(_schema)
+
+
+
+
+        repair_attempts = d.pop("repair_attempts", UNSET)
+
+        _grounding = d.pop("grounding", UNSET)
+        grounding: ExtractRequestGrounding | Unset
+        if isinstance(_grounding,  Unset):
+            grounding = UNSET
+        else:
+            grounding = ExtractRequestGrounding(_grounding)
+
+
+
+
+        file_id = d.pop("file_id", UNSET)
+
+        parse_job_id = d.pop("parse_job_id", UNSET)
+
+        _output_format = d.pop("output_format", UNSET)
+        output_format: ExtractRequestOutputFormat | Unset
+        if isinstance(_output_format,  Unset):
+            output_format = UNSET
+        else:
+            output_format = ExtractRequestOutputFormat(_output_format)
+
+
+
+
+        extract_request = cls(
+            pipeline_id=pipeline_id,
+            ocr_model=ocr_model,
+            ocr_options=ocr_options,
+            llm_model=llm_model,
+            llm_options=llm_options,
+            schema=schema,
+            repair_attempts=repair_attempts,
+            grounding=grounding,
+            file_id=file_id,
+            parse_job_id=parse_job_id,
+            output_format=output_format,
+        )
+
+        return extract_request

openparser/_generated/models/extract_request_grounding.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+class ExtractRequestGrounding(str, Enum):
+    FIELD = "field"
+    NONE = "none"
+
+    def __str__(self) -> str:
+        return str(self.value)

openparser/_generated/models/extract_request_llm_options.py

@@ -0,0 +1,84 @@
+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.extract_request_llm_options_reasoning_effort_type_1 import ExtractRequestLlmOptionsReasoningEffortType1
+from ..types import UNSET, Unset
+from typing import cast
+from typing import Literal, cast
+
+
+
+
+
+
+T = TypeVar("T", bound="ExtractRequestLlmOptions")
+
+
+
+@_attrs_define
+class ExtractRequestLlmOptions:
+    """
+        Attributes:
+            reasoning_effort (ExtractRequestLlmOptionsReasoningEffortType1 | Literal['auto'] | Unset):
+     """
+
+    reasoning_effort: ExtractRequestLlmOptionsReasoningEffortType1 | Literal['auto'] | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        reasoning_effort: Literal['auto'] | str | Unset
+        if isinstance(self.reasoning_effort, Unset):
+            reasoning_effort = UNSET
+        elif isinstance(self.reasoning_effort, ExtractRequestLlmOptionsReasoningEffortType1):
+            reasoning_effort = self.reasoning_effort.value
+        else:
+            reasoning_effort = self.reasoning_effort
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+        })
+        if reasoning_effort is not UNSET:
+            field_dict["reasoning_effort"] = reasoning_effort
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        def _parse_reasoning_effort(data: object) -> ExtractRequestLlmOptionsReasoningEffortType1 | Literal['auto'] | Unset:
+            if isinstance(data, Unset):
+                return data
+            reasoning_effort_type_0 = cast(Literal['auto'] , data)
+            if reasoning_effort_type_0 != 'auto':
+                raise ValueError(f"reasoning_effort_type_0 must match const 'auto', got '{reasoning_effort_type_0}'")
+            return reasoning_effort_type_0
+            if not isinstance(data, str):
+                raise TypeError()
+            reasoning_effort_type_1 = ExtractRequestLlmOptionsReasoningEffortType1(data)
+
+
+
+            return reasoning_effort_type_1
+
+        reasoning_effort = _parse_reasoning_effort(d.pop("reasoning_effort", UNSET))
+
+
+        extract_request_llm_options = cls(
+            reasoning_effort=reasoning_effort,
+        )
+
+        return extract_request_llm_options

openparser/_generated/models/extract_request_llm_options_reasoning_effort_type_1.py

@@ -0,0 +1,13 @@
+from enum import Enum
+
+class ExtractRequestLlmOptionsReasoningEffortType1(str, Enum):
+    HIGH = "high"
+    LOW = "low"
+    MAX = "max"
+    MEDIUM = "medium"
+    MINIMAL = "minimal"
+    NONE = "none"
+    XHIGH = "xhigh"
+
+    def __str__(self) -> str:
+        return str(self.value)

openparser/_generated/models/extract_request_ocr_options.py

@@ -0,0 +1,78 @@
+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
+
+
+
+
+
+
+T = TypeVar("T", bound="ExtractRequestOcrOptions")
+
+
+
+@_attrs_define
+class ExtractRequestOcrOptions:
+    """
+        Attributes:
+            image_block_ocr (bool | Unset):
+            chart_recognition (bool | Unset):
+            merge_layout_blocks (bool | Unset): Merge nearby cross-column or staggered text regions before recognition.
+                Defaults to false to preserve one-to-one text and bounding-box alignment.
+     """
+
+    image_block_ocr: bool | Unset = UNSET
+    chart_recognition: bool | Unset = UNSET
+    merge_layout_blocks: bool | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        image_block_ocr = self.image_block_ocr
+
+        chart_recognition = self.chart_recognition
+
+        merge_layout_blocks = self.merge_layout_blocks
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+        })
+        if image_block_ocr is not UNSET:
+            field_dict["image_block_ocr"] = image_block_ocr
+        if chart_recognition is not UNSET:
+            field_dict["chart_recognition"] = chart_recognition
+        if merge_layout_blocks is not UNSET:
+            field_dict["merge_layout_blocks"] = merge_layout_blocks
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        image_block_ocr = d.pop("image_block_ocr", UNSET)
+
+        chart_recognition = d.pop("chart_recognition", UNSET)
+
+        merge_layout_blocks = d.pop("merge_layout_blocks", UNSET)
+
+        extract_request_ocr_options = cls(
+            image_block_ocr=image_block_ocr,
+            chart_recognition=chart_recognition,
+            merge_layout_blocks=merge_layout_blocks,
+        )
+
+        return extract_request_ocr_options

openparser/_generated/models/extract_request_output_format.py

@@ -0,0 +1,8 @@
+from enum import Enum
+
+class ExtractRequestOutputFormat(str, Enum):
+    OPENPARSER1 = "openparser@1"
+    RAW = "raw"
+
+    def __str__(self) -> str:
+        return str(self.value)

openparser/_generated/models/extract_request_schema.py

@@ -0,0 +1,65 @@
+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
+
+
+
+
+
+
+
+T = TypeVar("T", bound="ExtractRequestSchema")
+
+
+
+@_attrs_define
+class ExtractRequestSchema:
+    """
+     """
+
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        d = dict(src_dict)
+        extract_request_schema = cls(
+        )
+
+
+        extract_request_schema.additional_properties = d
+        return extract_request_schema
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties

openparser/_generated/models/extract_sync_body.py

@@ -0,0 +1,136 @@
+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
+import json
+from .. import types
+
+from ..types import UNSET, Unset
+
+from ..types import File, FileTypes
+from ..types import UNSET, Unset
+from io import BytesIO
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.extract_request import ExtractRequest
+
+
+
+
+
+T = TypeVar("T", bound="ExtractSyncBody")
+
+
+
+@_attrs_define
+class ExtractSyncBody:
+    """
+        Attributes:
+            request (ExtractRequest): Single extract config. Provide either `pipeline_id` or inline extraction config.
+                The source is exactly one of multipart file bytes, `file_id`, or tenant-owned succeeded
+                `parse_job_id`. Parse reuse is single-extract-only, forbids `ocr_model` / `ocr_options`,
+                does not run OCR, and adds no page charge. `parse_job_id` is part of idempotency identity.
+            file (File | Unset): Source document bytes (PDF, PNG, or JPEG). Required unless `request.file_id`
+                references an existing Eigenpal reusable file.
+     """
+
+    request: ExtractRequest
+    file: File | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.extract_request import ExtractRequest
+        request = self.request.to_dict()
+
+        file: FileTypes | Unset = UNSET
+        if not isinstance(self.file, Unset):
+            file = self.file.to_tuple()
+
+
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update({
+            "request": request,
+        })
+        if file is not UNSET:
+            field_dict["file"] = file
+
+        return field_dict
+
+
+    def to_multipart(self) -> types.RequestFiles:
+        from ..models.extract_request import ExtractRequest
+        files: types.RequestFiles = []
+
+        files.append(("request", (None, json.dumps( self.request.to_dict()).encode(), "application/json")))
+
+
+
+        if not isinstance(self.file, Unset):
+            files.append(("file", self.file.to_tuple()))
+
+
+
+
+        for prop_name, prop in self.additional_properties.items():
+            files.append((prop_name, (None, str(prop).encode(), "text/plain")))
+
+
+
+        return files
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.extract_request import ExtractRequest
+        d = dict(src_dict)
+        request = ExtractRequest.from_dict(d.pop("request"))
+
+
+
+
+        _file = d.pop("file", UNSET)
+        file: File | Unset
+        if isinstance(_file,  Unset):
+            file = UNSET
+        else:
+            file = File(
+             payload = BytesIO(_file)
+        )
+
+
+
+
+        extract_sync_body = cls(
+            request=request,
+            file=file,
+        )
+
+
+        extract_sync_body.additional_properties = d
+        return extract_sync_body
+
+    @property
+    def additional_keys(self) -> list[str]:
+        return list(self.additional_properties.keys())
+
+    def __getitem__(self, key: str) -> Any:
+        return self.additional_properties[key]
+
+    def __setitem__(self, key: str, value: Any) -> None:
+        self.additional_properties[key] = value
+
+    def __delitem__(self, key: str) -> None:
+        del self.additional_properties[key]
+
+    def __contains__(self, key: str) -> bool:
+        return key in self.additional_properties