openparser-sdk 0.0.1__py3-none-any.whl

openparser/_generated/models/update_extraction_pipeline_request.py

@@ -0,0 +1,227 @@
+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.update_extraction_pipeline_request_grounding import UpdateExtractionPipelineRequestGrounding
+from ..types import UNSET, Unset
+from typing import cast
+
+if TYPE_CHECKING:
+  from ..models.update_extraction_pipeline_request_llm_options_type_0 import UpdateExtractionPipelineRequestLlmOptionsType0
+  from ..models.update_extraction_pipeline_request_ocr_options_type_0 import UpdateExtractionPipelineRequestOcrOptionsType0
+  from ..models.update_extraction_pipeline_request_schema import UpdateExtractionPipelineRequestSchema
+
+
+
+
+
+T = TypeVar("T", bound="UpdateExtractionPipelineRequest")
+
+
+
+@_attrs_define
+class UpdateExtractionPipelineRequest:
+    """ Partial update; at least one field required. Successful updates bump `version`.
+
+        Attributes:
+            name (str | Unset):
+            slug (None | str | Unset):
+            ocr_model (str | Unset):
+            ocr_options (None | Unset | UpdateExtractionPipelineRequestOcrOptionsType0):
+            llm_model (str | Unset):
+            llm_options (None | Unset | UpdateExtractionPipelineRequestLlmOptionsType0):
+            schema (UpdateExtractionPipelineRequestSchema | Unset): Replacement extraction schema. Root must be an object
+                schema with explicit `properties`
+                and at least one named property. Merged pipeline config is re-validated on every update.
+            repair_attempts (int | Unset):
+            grounding (UpdateExtractionPipelineRequestGrounding | Unset):
+     """
+
+    name: str | Unset = UNSET
+    slug: None | str | Unset = UNSET
+    ocr_model: str | Unset = UNSET
+    ocr_options: None | Unset | UpdateExtractionPipelineRequestOcrOptionsType0 = UNSET
+    llm_model: str | Unset = UNSET
+    llm_options: None | Unset | UpdateExtractionPipelineRequestLlmOptionsType0 = UNSET
+    schema: UpdateExtractionPipelineRequestSchema | Unset = UNSET
+    repair_attempts: int | Unset = UNSET
+    grounding: UpdateExtractionPipelineRequestGrounding | Unset = UNSET
+
+
+
+
+
+    def to_dict(self) -> dict[str, Any]:
+        from ..models.update_extraction_pipeline_request_llm_options_type_0 import UpdateExtractionPipelineRequestLlmOptionsType0
+        from ..models.update_extraction_pipeline_request_ocr_options_type_0 import UpdateExtractionPipelineRequestOcrOptionsType0
+        from ..models.update_extraction_pipeline_request_schema import UpdateExtractionPipelineRequestSchema
+        name = self.name
+
+        slug: None | str | Unset
+        if isinstance(self.slug, Unset):
+            slug = UNSET
+        else:
+            slug = self.slug
+
+        ocr_model = self.ocr_model
+
+        ocr_options: dict[str, Any] | None | Unset
+        if isinstance(self.ocr_options, Unset):
+            ocr_options = UNSET
+        elif isinstance(self.ocr_options, UpdateExtractionPipelineRequestOcrOptionsType0):
+            ocr_options = self.ocr_options.to_dict()
+        else:
+            ocr_options = self.ocr_options
+
+        llm_model = self.llm_model
+
+        llm_options: dict[str, Any] | None | Unset
+        if isinstance(self.llm_options, Unset):
+            llm_options = UNSET
+        elif isinstance(self.llm_options, UpdateExtractionPipelineRequestLlmOptionsType0):
+            llm_options = self.llm_options.to_dict()
+        else:
+            llm_options = self.llm_options
+
+        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({
+        })
+        if name is not UNSET:
+            field_dict["name"] = name
+        if slug is not UNSET:
+            field_dict["slug"] = slug
+        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.update_extraction_pipeline_request_llm_options_type_0 import UpdateExtractionPipelineRequestLlmOptionsType0
+        from ..models.update_extraction_pipeline_request_ocr_options_type_0 import UpdateExtractionPipelineRequestOcrOptionsType0
+        from ..models.update_extraction_pipeline_request_schema import UpdateExtractionPipelineRequestSchema
+        d = dict(src_dict)
+        name = d.pop("name", UNSET)
+
+        def _parse_slug(data: object) -> None | str | Unset:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            return cast(None | str | Unset, data)
+
+        slug = _parse_slug(d.pop("slug", UNSET))
+
+
+        ocr_model = d.pop("ocr_model", UNSET)
+
+        def _parse_ocr_options(data: object) -> None | Unset | UpdateExtractionPipelineRequestOcrOptionsType0:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            try:
+                if not isinstance(data, dict):
+                    raise TypeError()
+                ocr_options_type_0 = UpdateExtractionPipelineRequestOcrOptionsType0.from_dict(data)
+
+
+
+                return ocr_options_type_0
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            return cast(None | Unset | UpdateExtractionPipelineRequestOcrOptionsType0, data)
+
+        ocr_options = _parse_ocr_options(d.pop("ocr_options", UNSET))
+
+
+        llm_model = d.pop("llm_model", UNSET)
+
+        def _parse_llm_options(data: object) -> None | Unset | UpdateExtractionPipelineRequestLlmOptionsType0:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            try:
+                if not isinstance(data, dict):
+                    raise TypeError()
+                llm_options_type_0 = UpdateExtractionPipelineRequestLlmOptionsType0.from_dict(data)
+
+
+
+                return llm_options_type_0
+            except (TypeError, ValueError, AttributeError, KeyError):
+                pass
+            return cast(None | Unset | UpdateExtractionPipelineRequestLlmOptionsType0, data)
+
+        llm_options = _parse_llm_options(d.pop("llm_options", UNSET))
+
+
+        _schema = d.pop("schema", UNSET)
+        schema: UpdateExtractionPipelineRequestSchema | Unset
+        if isinstance(_schema,  Unset):
+            schema = UNSET
+        else:
+            schema = UpdateExtractionPipelineRequestSchema.from_dict(_schema)
+
+
+
+
+        repair_attempts = d.pop("repair_attempts", UNSET)
+
+        _grounding = d.pop("grounding", UNSET)
+        grounding: UpdateExtractionPipelineRequestGrounding | Unset
+        if isinstance(_grounding,  Unset):
+            grounding = UNSET
+        else:
+            grounding = UpdateExtractionPipelineRequestGrounding(_grounding)
+
+
+
+
+        update_extraction_pipeline_request = cls(
+            name=name,
+            slug=slug,
+            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 update_extraction_pipeline_request

openparser/_generated/models/update_extraction_pipeline_request_grounding.py

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

openparser/_generated/models/update_extraction_pipeline_request_llm_options_type_0.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.update_extraction_pipeline_request_llm_options_type_0_reasoning_effort_type_1 import UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1
+from ..types import UNSET, Unset
+from typing import cast
+from typing import Literal, cast
+
+
+
+
+
+
+T = TypeVar("T", bound="UpdateExtractionPipelineRequestLlmOptionsType0")
+
+
+
+@_attrs_define
+class UpdateExtractionPipelineRequestLlmOptionsType0:
+    """
+        Attributes:
+            reasoning_effort (Literal['auto'] | Unset | UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1):
+     """
+
+    reasoning_effort: Literal['auto'] | Unset | UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1 = 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, UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1):
+            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) -> Literal['auto'] | Unset | UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1:
+            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 = UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1(data)
+
+
+
+            return reasoning_effort_type_1
+
+        reasoning_effort = _parse_reasoning_effort(d.pop("reasoning_effort", UNSET))
+
+
+        update_extraction_pipeline_request_llm_options_type_0 = cls(
+            reasoning_effort=reasoning_effort,
+        )
+
+        return update_extraction_pipeline_request_llm_options_type_0

openparser/_generated/models/update_extraction_pipeline_request_llm_options_type_0_reasoning_effort_type_1.py

@@ -0,0 +1,13 @@
+from enum import Enum
+
+class UpdateExtractionPipelineRequestLlmOptionsType0ReasoningEffortType1(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/update_extraction_pipeline_request_ocr_options_type_0.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="UpdateExtractionPipelineRequestOcrOptionsType0")
+
+
+
+@_attrs_define
+class UpdateExtractionPipelineRequestOcrOptionsType0:
+    """
+        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)
+
+        update_extraction_pipeline_request_ocr_options_type_0 = cls(
+            image_block_ocr=image_block_ocr,
+            chart_recognition=chart_recognition,
+            merge_layout_blocks=merge_layout_blocks,
+        )
+
+        return update_extraction_pipeline_request_ocr_options_type_0

openparser/_generated/models/update_extraction_pipeline_request_schema.py

@@ -0,0 +1,67 @@
+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="UpdateExtractionPipelineRequestSchema")
+
+
+
+@_attrs_define
+class UpdateExtractionPipelineRequestSchema:
+    """ Replacement extraction schema. Root must be an object schema with explicit `properties`
+    and at least one named property. Merged pipeline config is re-validated on every update.
+
+     """
+
+    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)
+        update_extraction_pipeline_request_schema = cls(
+        )
+
+
+        update_extraction_pipeline_request_schema.additional_properties = d
+        return update_extraction_pipeline_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/py.typed

@@ -0,0 +1 @@
+# Marker file for PEP 561

openparser/_generated/types.py

@@ -0,0 +1,53 @@
+""" Contains some shared types for properties """
+
+from collections.abc import Mapping, MutableMapping
+from http import HTTPStatus
+from typing import BinaryIO, Generic, TypeVar, Literal, IO
+
+from attrs import define
+
+
+class Unset:
+    def __bool__(self) -> Literal[False]:
+        return False
+
+
+UNSET: Unset = Unset()
+
+# The types that `httpx.Client(files=)` can accept, copied from that library.
+FileContent = IO[bytes] | bytes | str
+FileTypes = (
+    # (filename, file (or bytes), content_type)
+    tuple[str | None, FileContent, str | None]
+    # (filename, file (or bytes), content_type, headers)
+    | tuple[str | None, FileContent, str | None, Mapping[str, str]]
+)
+RequestFiles = list[tuple[str, FileTypes]]
+
+@define
+class File:
+    """ Contains information for file uploads """
+
+    payload: BinaryIO
+    file_name: str | None = None
+    mime_type: str | None = None
+
+    def to_tuple(self) -> FileTypes:
+        """ Return a tuple representation that httpx will accept for multipart/form-data """
+        return self.file_name, self.payload, self.mime_type
+
+
+T = TypeVar("T")
+
+
+@define
+class Response(Generic[T]):
+    """ A response from an endpoint """
+
+    status_code: HTTPStatus
+    content: bytes
+    headers: MutableMapping[str, str]
+    parsed: T | None
+
+
+__all__ = ["UNSET", "File", "FileTypes", "RequestFiles", "Response", "Unset"]

openparser/_telemetry.py

@@ -0,0 +1,34 @@
+"""SDK telemetry headers attached to every outbound request."""
+
+from __future__ import annotations
+
+import platform
+import sys
+
+SDK_LANGUAGE = "python"
+SDK_VERSION = "0.0.1"
+
+
+def _detect_runtime() -> str:
+    impl = platform.python_implementation().lower()
+    name = "python" if impl == "cpython" else impl
+    v = sys.version_info
+    return f"{name}-{v.major}.{v.minor}.{v.micro}"
+
+
+def _detect_os() -> str:
+    system = platform.system().lower() or "unknown"
+    machine = platform.machine().lower() or "unknown"
+    return f"{system}-{machine}"
+
+
+def build_telemetry_headers() -> dict[str, str]:
+    runtime = _detect_runtime()
+    os_name = _detect_os()
+    return {
+        "X-OpenParser-Sdk": SDK_LANGUAGE,
+        "X-OpenParser-Sdk-Version": SDK_VERSION,
+        "X-OpenParser-Sdk-Runtime": runtime,
+        "X-OpenParser-Sdk-Os": os_name,
+        "User-Agent": f"openparser-sdk-python/{SDK_VERSION} ({runtime}; {os_name})",
+    }