openparser-sdk 0.0.1__py3-none-any.whl

openparser/_generated/models/extract_async_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="ExtractAsyncBody")
+
+
+
+@_attrs_define
+class ExtractAsyncBody:
+    """
+        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_async_body = cls(
+            request=request,
+            file=file,
+        )
+
+
+        extract_async_body.additional_properties = d
+        return extract_async_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

openparser/_generated/models/extract_batch_body.py

@@ -0,0 +1,143 @@
+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_batch_request import ExtractBatchRequest
+
+
+
+
+
+T = TypeVar("T", bound="ExtractBatchBody")
+
+
+
+@_attrs_define
+class ExtractBatchBody:
+    """
+        Attributes:
+            request (ExtractBatchRequest):
+            files (list[File] | Unset): Ordered uploaded files referenced by `file_index` in the batch request. Each file
+                is limited to 50 MiB and total multipart body content is limited to 100 MiB.
+                Omit when every batch item supplies `file_id` instead.
+     """
+
+    request: ExtractBatchRequest
+    files: list[File] | Unset = UNSET
+    additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.extract_batch_request import ExtractBatchRequest
+        request = self.request.to_dict()
+
+        files: list[FileTypes] | Unset = UNSET
+        if not isinstance(self.files, Unset):
+            files = []
+            for files_item_data in self.files:
+                files_item = files_item_data.to_tuple()
+
+                files.append(files_item)
+
+
+
+
+        field_dict: dict[str, Any] = {}
+        field_dict.update(self.additional_properties)
+        field_dict.update({
+            "request": request,
+        })
+        if files is not UNSET:
+            field_dict["files"] = files
+
+        return field_dict
+
+
+    def to_multipart(self) -> types.RequestFiles:
+        from ..models.extract_batch_request import ExtractBatchRequest
+        files: types.RequestFiles = []
+
+        files.append(("request", (None, json.dumps( self.request.to_dict()).encode(), "application/json")))
+
+
+
+        if not isinstance(self.files, Unset):
+            for files_item_element in self.files:
+                files.append(("files", files_item_element.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_batch_request import ExtractBatchRequest
+        d = dict(src_dict)
+        request = ExtractBatchRequest.from_dict(d.pop("request"))
+
+
+
+
+        _files = d.pop("files", UNSET)
+        files: list[File] | Unset = UNSET
+        if _files is not UNSET:
+            files = []
+            for files_item_data in _files:
+                files_item = File(
+                     payload = BytesIO(files_item_data)
+                )
+
+
+
+                files.append(files_item)
+
+
+        extract_batch_body = cls(
+            request=request,
+            files=files,
+        )
+
+
+        extract_batch_body.additional_properties = d
+        return extract_batch_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

openparser/_generated/models/extract_batch_item.py

@@ -0,0 +1,207 @@
+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_batch_item_grounding import ExtractBatchItemGrounding
+from ..types import UNSET, Unset
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.extract_batch_item_llm_options import ExtractBatchItemLlmOptions
+  from ..models.extract_batch_item_ocr_options import ExtractBatchItemOcrOptions
+  from ..models.extract_batch_item_schema import ExtractBatchItemSchema
+
+
+
+
+
+T = TypeVar("T", bound="ExtractBatchItem")
+
+
+
+@_attrs_define
+class ExtractBatchItem:
+    """ Per-item file-backed extract config with the same `pipeline_id` XOR inline rules as
+    single extract. Sources are `file_index` or `file_id`; `parse_job_id` is not supported
+    in batch. No parent-level batch pipeline in v1.
+
+        Attributes:
+            client_item_id (str):
+            file_index (int | Unset): Zero-based index into the uploaded `files` array. Exactly one of `file_index` or
+                `file_id` is required per item.
+            file_id (str | Unset):
+            pipeline_id (str | Unset): Saved extraction pipeline id; mutually exclusive with inline extract fields.
+            ocr_model (str | Unset):
+            ocr_options (ExtractBatchItemOcrOptions | Unset):
+            llm_model (str | Unset):
+            llm_options (ExtractBatchItemLlmOptions | Unset):
+            schema (ExtractBatchItemSchema | Unset):
+            repair_attempts (int | Unset):
+            grounding (ExtractBatchItemGrounding | Unset): Optional field grounding mode. Defaults to `none`. `field` opts
+                into verified
+                per-leaf citations and is part of idempotency identity.
+     """
+
+    client_item_id: str
+    file_index: int | Unset = UNSET
+    file_id: str | Unset = UNSET
+    pipeline_id: str | Unset = UNSET
+    ocr_model: str | Unset = UNSET
+    ocr_options: ExtractBatchItemOcrOptions | Unset = UNSET
+    llm_model: str | Unset = UNSET
+    llm_options: ExtractBatchItemLlmOptions | Unset = UNSET
+    schema: ExtractBatchItemSchema | Unset = UNSET
+    repair_attempts: int | Unset = UNSET
+    grounding: ExtractBatchItemGrounding | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.extract_batch_item_llm_options import ExtractBatchItemLlmOptions
+        from ..models.extract_batch_item_ocr_options import ExtractBatchItemOcrOptions
+        from ..models.extract_batch_item_schema import ExtractBatchItemSchema
+        client_item_id = self.client_item_id
+
+        file_index = self.file_index
+
+        file_id = self.file_id
+
+        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
+
+
+
+        field_dict: dict[str, Any] = {}
+
+        field_dict.update({
+            "client_item_id": client_item_id,
+        })
+        if file_index is not UNSET:
+            field_dict["file_index"] = file_index
+        if file_id is not UNSET:
+            field_dict["file_id"] = file_id
+        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
+
+        return field_dict
+
+
+
+    @classmethod
+    def from_dict(cls: type[T], src_dict: Mapping[str, Any]) -> T:
+        from ..models.extract_batch_item_llm_options import ExtractBatchItemLlmOptions
+        from ..models.extract_batch_item_ocr_options import ExtractBatchItemOcrOptions
+        from ..models.extract_batch_item_schema import ExtractBatchItemSchema
+        d = dict(src_dict)
+        client_item_id = d.pop("client_item_id")
+
+        file_index = d.pop("file_index", UNSET)
+
+        file_id = d.pop("file_id", UNSET)
+
+        pipeline_id = d.pop("pipeline_id", UNSET)
+
+        ocr_model = d.pop("ocr_model", UNSET)
+
+        _ocr_options = d.pop("ocr_options", UNSET)
+        ocr_options: ExtractBatchItemOcrOptions | Unset
+        if isinstance(_ocr_options,  Unset):
+            ocr_options = UNSET
+        else:
+            ocr_options = ExtractBatchItemOcrOptions.from_dict(_ocr_options)
+
+
+
+
+        llm_model = d.pop("llm_model", UNSET)
+
+        _llm_options = d.pop("llm_options", UNSET)
+        llm_options: ExtractBatchItemLlmOptions | Unset
+        if isinstance(_llm_options,  Unset):
+            llm_options = UNSET
+        else:
+            llm_options = ExtractBatchItemLlmOptions.from_dict(_llm_options)
+
+
+
+
+        _schema = d.pop("schema", UNSET)
+        schema: ExtractBatchItemSchema | Unset
+        if isinstance(_schema,  Unset):
+            schema = UNSET
+        else:
+            schema = ExtractBatchItemSchema.from_dict(_schema)
+
+
+
+
+        repair_attempts = d.pop("repair_attempts", UNSET)
+
+        _grounding = d.pop("grounding", UNSET)
+        grounding: ExtractBatchItemGrounding | Unset
+        if isinstance(_grounding,  Unset):
+            grounding = UNSET
+        else:
+            grounding = ExtractBatchItemGrounding(_grounding)
+
+
+
+
+        extract_batch_item = cls(
+            client_item_id=client_item_id,
+            file_index=file_index,
+            file_id=file_id,
+            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,
+        )
+
+        return extract_batch_item

openparser/_generated/models/extract_batch_item_grounding.py

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

openparser/_generated/models/extract_batch_item_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_batch_item_llm_options_reasoning_effort_type_1 import ExtractBatchItemLlmOptionsReasoningEffortType1
+from ..types import UNSET, Unset
+from typing import cast
+from typing import Literal, cast
+
+
+
+
+
+
+T = TypeVar("T", bound="ExtractBatchItemLlmOptions")
+
+
+
+@_attrs_define
+class ExtractBatchItemLlmOptions:
+    """
+        Attributes:
+            reasoning_effort (ExtractBatchItemLlmOptionsReasoningEffortType1 | Literal['auto'] | Unset):
+     """
+
+    reasoning_effort: ExtractBatchItemLlmOptionsReasoningEffortType1 | 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, ExtractBatchItemLlmOptionsReasoningEffortType1):
+            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) -> ExtractBatchItemLlmOptionsReasoningEffortType1 | 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 = ExtractBatchItemLlmOptionsReasoningEffortType1(data)
+
+
+
+            return reasoning_effort_type_1
+
+        reasoning_effort = _parse_reasoning_effort(d.pop("reasoning_effort", UNSET))
+
+
+        extract_batch_item_llm_options = cls(
+            reasoning_effort=reasoning_effort,
+        )
+
+        return extract_batch_item_llm_options

openparser/_generated/models/extract_batch_item_llm_options_reasoning_effort_type_1.py

@@ -0,0 +1,13 @@
+from enum import Enum
+
+class ExtractBatchItemLlmOptionsReasoningEffortType1(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_batch_item_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="ExtractBatchItemOcrOptions")
+
+
+
+@_attrs_define
+class ExtractBatchItemOcrOptions:
+    """
+        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_batch_item_ocr_options = cls(
+            image_block_ocr=image_block_ocr,
+            chart_recognition=chart_recognition,
+            merge_layout_blocks=merge_layout_blocks,
+        )
+
+        return extract_batch_item_ocr_options