SDK regeneration

.fern/metadata.json

@@ -12,6 +12,6 @@
       "enum_type": "forward_compatible_python_enums"
     }
   },
-  "originGitCommit": "a5c1143a7b724689db7c5e4cee897834882c9d69",
-  "sdkVersion": "1.17.0"
+  "originGitCommit": "204f01f5a6e9ad6585d71b0ad6315aef1be1f537",
+  "sdkVersion": "1.18.0"
 }

pyproject.toml

@@ -4,7 +4,7 @@ dynamic = ["version"]
 
 [tool.poetry]
 name = "extend_ai"
-version = "1.17.0"
+version = "1.18.0"
 description = "Official Python SDK for Extend (extend.ai) — the document processing API. Parse, extract, classify, split, and edit PDFs and 35+ file types"
 readme = "README.md"
 authors = []

reference.md

@@ -7150,7 +7150,7 @@ Example: `"invoice"`
 
 Run a workflow. A workflow is a sequence of steps that process files and data in a specific order to achieve a desired outcome.
 
-Pass `file` for a single document, or `package` to process 2-50 files together as one package in a single run. Exactly one of `file` or `package` must be provided.
+Pass `file` for a single document use case (more common), or `package` to process 2-50 files together as one package in a single run where context across files is used together to determine final output. Exactly one of `file` or `package` must be provided.
 
 The request returns immediately with a `PROCESSING` status. Use webhooks or poll the Get Workflow Run endpoint for results.
 </dd>

src/extend_ai/__init__.py

@@ -276,6 +276,8 @@
         ParseRunFailedWebhookEvent,
         ParseRunMetrics,
         ParseRunOutput,
+        ParseRunOutputMetadata,
+        ParseRunOutputMetadataPagesItem,
         ParseRunOutputOcr,
         ParseRunOutputOcrWordsItem,
         ParseRunProcessedWebhookEvent,
@@ -767,6 +769,8 @@
         ParseResultParams,
         ParseRunFailedWebhookEventParams,
         ParseRunMetricsParams,
+        ParseRunOutputMetadataPagesItemParams,
+        ParseRunOutputMetadataParams,
         ParseRunOutputOcrParams,
         ParseRunOutputOcrWordsItemParams,
         ParseRunOutputParams,
@@ -1440,6 +1444,10 @@
     "ParseRunMetrics": ".types",
     "ParseRunMetricsParams": ".requests",
     "ParseRunOutput": ".types",
+    "ParseRunOutputMetadata": ".types",
+    "ParseRunOutputMetadataPagesItem": ".types",
+    "ParseRunOutputMetadataPagesItemParams": ".requests",
+    "ParseRunOutputMetadataParams": ".requests",
     "ParseRunOutputOcr": ".types",
     "ParseRunOutputOcrParams": ".requests",
     "ParseRunOutputOcrWordsItem": ".types",
@@ -2335,6 +2343,10 @@ def __dir__():
     "ParseRunMetrics",
     "ParseRunMetricsParams",
     "ParseRunOutput",
+    "ParseRunOutputMetadata",
+    "ParseRunOutputMetadataPagesItem",
+    "ParseRunOutputMetadataPagesItemParams",
+    "ParseRunOutputMetadataParams",
     "ParseRunOutputOcr",
     "ParseRunOutputOcrParams",
     "ParseRunOutputOcrWordsItem",

src/extend_ai/core/client_wrapper.py

@@ -26,12 +26,12 @@ def get_headers(self) -> typing.Dict[str, str]:
         import platform
 
         headers: typing.Dict[str, str] = {
-            "User-Agent": "extend_ai/1.17.0",
+            "User-Agent": "extend_ai/1.18.0",
             "X-Fern-Language": "Python",
             "X-Fern-Runtime": f"python/{platform.python_version()}",
             "X-Fern-Platform": f"{platform.system().lower()}/{platform.release()}",
             "X-Fern-SDK-Name": "extend_ai",
-            "X-Fern-SDK-Version": "1.17.0",
+            "X-Fern-SDK-Version": "1.18.0",
             **(self.get_custom_headers() or {}),
         }
         headers["Authorization"] = f"Bearer {self._get_token()}"

src/extend_ai/requests/__init__.py

@@ -296,6 +296,8 @@
     from .parse_run_failed_webhook_event import ParseRunFailedWebhookEventParams
     from .parse_run_metrics import ParseRunMetricsParams
     from .parse_run_output import ParseRunOutputParams
+    from .parse_run_output_metadata import ParseRunOutputMetadataParams
+    from .parse_run_output_metadata_pages_item import ParseRunOutputMetadataPagesItemParams
     from .parse_run_output_ocr import ParseRunOutputOcrParams
     from .parse_run_output_ocr_words_item import ParseRunOutputOcrWordsItemParams
     from .parse_run_processed_webhook_event import ParseRunProcessedWebhookEventParams
@@ -724,6 +726,8 @@
     "ParseResultParams": ".parse_result",
     "ParseRunFailedWebhookEventParams": ".parse_run_failed_webhook_event",
     "ParseRunMetricsParams": ".parse_run_metrics",
+    "ParseRunOutputMetadataPagesItemParams": ".parse_run_output_metadata_pages_item",
+    "ParseRunOutputMetadataParams": ".parse_run_output_metadata",
     "ParseRunOutputOcrParams": ".parse_run_output_ocr",
     "ParseRunOutputOcrWordsItemParams": ".parse_run_output_ocr_words_item",
     "ParseRunOutputParams": ".parse_run_output",
@@ -1172,6 +1176,8 @@ def __dir__():
     "ParseResultParams",
     "ParseRunFailedWebhookEventParams",
     "ParseRunMetricsParams",
+    "ParseRunOutputMetadataPagesItemParams",
+    "ParseRunOutputMetadataParams",
     "ParseRunOutputOcrParams",
     "ParseRunOutputOcrWordsItemParams",
     "ParseRunOutputParams",

src/extend_ai/requests/data_retention.py

@@ -8,7 +8,7 @@ class DataRetentionParams(typing_extensions.TypedDict):
     """
     Controls data retention for this run. When omitted or set to `workspace_default`, Extend uses your workspace's configured retention policy. Set `mode` to `zero` to request zero data retention for the run, which deletes supported run data after processing instead of retaining it under the workspace policy.
 
-    Zero data retention is only available for eligible organizations and plans. If your organization is not eligible, the request will fail with a 400 error.
+    Zero data retention is available to all customers on paid plans upon request. If you're on a free plan, the request will fail with a 400 error. If you'd like to request ZDR to be enabled, please reach out to support@extend.ai.
     """
 
     mode: typing_extensions.NotRequired[DataRetentionMode]

src/extend_ai/requests/parse_run_output.py

@@ -4,6 +4,7 @@
 
 import typing_extensions
 from .chunk import ChunkParams
+from .parse_run_output_metadata import ParseRunOutputMetadataParams
 from .parse_run_output_ocr import ParseRunOutputOcrParams
 
 
@@ -23,3 +24,8 @@ class ParseRunOutputParams(typing_extensions.TypedDict):
     """
     Raw OCR data from the parsing process. Only included when `returnOcr` is configured in the parse config's advanced options.
     """
+
+    metadata: typing_extensions.NotRequired[typing.Optional[ParseRunOutputMetadataParams]]
+    """
+    Rotation, dimension, and file-type metadata about the parse output. `null` for parse runs that completed before this field was introduced.
+    """

src/extend_ai/requests/parse_run_output_metadata.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..core.serialization import FieldMetadata
+from .parse_run_output_metadata_pages_item import ParseRunOutputMetadataPagesItemParams
+
+
+class ParseRunOutputMetadataParams(typing_extensions.TypedDict):
+    """
+    Rotation, dimension, and file-type metadata about the parse output. `null` for parse runs that completed before this field was introduced.
+    """
+
+    original_mime_type: typing_extensions.NotRequired[
+        typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="originalMimeType")]
+    ]
+    """
+    The file's media type before any format conversion.
+    """
+
+    final_mime_type: typing_extensions.NotRequired[
+        typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="finalMimeType")]
+    ]
+    """
+    The file's media type after any format conversion.
+    """
+
+    pages: typing_extensions.NotRequired[typing.Optional[typing.Sequence[ParseRunOutputMetadataPagesItemParams]]]
+    """
+    Per-page rotation and original-dimension info. Set when file is a PDF or was converted to PDF.
+    """

src/extend_ai/requests/parse_run_output_metadata_pages_item.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..core.serialization import FieldMetadata
+
+
+class ParseRunOutputMetadataPagesItemParams(typing_extensions.TypedDict):
+    number: int
+    """
+    The page number this entry describes.
+    """
+
+    rotation_applied: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="rotationApplied")]
+    """
+    Degrees Extend rotated the page clockwise to make it upright. `0` if rotation detection ran and the page was already upright; `null` if rotation detection was disabled for this run.
+    """
+
+    original_page_width: typing_extensions.Annotated[float, FieldMetadata(alias="originalPageWidth")]
+    """
+    The file's true page width, independent of rendering resolution.
+    """
+
+    original_page_height: typing_extensions.Annotated[float, FieldMetadata(alias="originalPageHeight")]
+    """
+    The file's true page height, independent of rendering resolution.
+    """
+
+    dpi: float
+    """
+    The DPI that `boundingBox`/`polygon` coordinates on this page are scaled to. Multiply `originalPageWidth`/`originalPageHeight` by `dpi / 72` to convert them into that same coordinate space.
+    """

src/extend_ai/requests/parse_run_output_ocr_words_item.py

@@ -25,3 +25,8 @@ class ParseRunOutputOcrWordsItemParams(typing_extensions.TypedDict):
     """
     The page number where the word was detected.
     """
+
+    block_id: typing_extensions.NotRequired[typing_extensions.Annotated[str, FieldMetadata(alias="blockId")]]
+    """
+    The `id` of the block (see the `Block` schema) this word was assigned to, based on bounding-box overlap. Omitted when the word doesn't fall within any block's bounding box.
+    """

src/extend_ai/requests/workflow_run_package.py

@@ -15,7 +15,7 @@ class WorkflowRunPackageParams(typing_extensions.TypedDict):
 
     files: typing.Sequence[WorkflowRunPackageFilesItemParams]
     """
-    The files to process, in submission order. Each entry can be a URL or an existing Extend file ID. Raw text and base64 inputs are not supported for package runs.
+    The files to process. Each entry can be a URL or an existing Extend file ID. Raw text and base64 inputs are not supported for package runs.
 
     Duplicate file IDs and duplicate URLs are rejected — each file may appear only once. A URL and a file ID are never treated as duplicates of each other, even if they resolve to the same document.
     """

src/extend_ai/types/__init__.py

@@ -379,6 +379,8 @@
     from .parse_run_failed_webhook_event import ParseRunFailedWebhookEvent
     from .parse_run_metrics import ParseRunMetrics
     from .parse_run_output import ParseRunOutput
+    from .parse_run_output_metadata import ParseRunOutputMetadata
+    from .parse_run_output_metadata_pages_item import ParseRunOutputMetadataPagesItem
     from .parse_run_output_ocr import ParseRunOutputOcr
     from .parse_run_output_ocr_words_item import ParseRunOutputOcrWordsItem
     from .parse_run_processed_webhook_event import ParseRunProcessedWebhookEvent
@@ -904,6 +906,8 @@
     "ParseRunFailedWebhookEvent": ".parse_run_failed_webhook_event",
     "ParseRunMetrics": ".parse_run_metrics",
     "ParseRunOutput": ".parse_run_output",
+    "ParseRunOutputMetadata": ".parse_run_output_metadata",
+    "ParseRunOutputMetadataPagesItem": ".parse_run_output_metadata_pages_item",
     "ParseRunOutputOcr": ".parse_run_output_ocr",
     "ParseRunOutputOcrWordsItem": ".parse_run_output_ocr_words_item",
     "ParseRunProcessedWebhookEvent": ".parse_run_processed_webhook_event",
@@ -1447,6 +1451,8 @@ def __dir__():
     "ParseRunFailedWebhookEvent",
     "ParseRunMetrics",
     "ParseRunOutput",
+    "ParseRunOutputMetadata",
+    "ParseRunOutputMetadataPagesItem",
     "ParseRunOutputOcr",
     "ParseRunOutputOcrWordsItem",
     "ParseRunProcessedWebhookEvent",

src/extend_ai/types/data_retention.py

@@ -12,7 +12,7 @@ class DataRetention(UncheckedBaseModel):
     """
     Controls data retention for this run. When omitted or set to `workspace_default`, Extend uses your workspace's configured retention policy. Set `mode` to `zero` to request zero data retention for the run, which deletes supported run data after processing instead of retaining it under the workspace policy.
 
-    Zero data retention is only available for eligible organizations and plans. If your organization is not eligible, the request will fail with a 400 error.
+    Zero data retention is available to all customers on paid plans upon request. If you're on a free plan, the request will fail with a 400 error. If you'd like to request ZDR to be enabled, please reach out to support@extend.ai.
     """
 
     mode: typing.Optional[DataRetentionMode] = pydantic.Field(default=None)

src/extend_ai/types/parse_run_output.py

@@ -8,6 +8,7 @@
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, update_forward_refs
 from ..core.unchecked_base_model import UncheckedBaseModel
 from .chunk import Chunk
+from .parse_run_output_metadata import ParseRunOutputMetadata
 from .parse_run_output_ocr import ParseRunOutputOcr
 
 
@@ -28,6 +29,11 @@ class ParseRunOutput(UncheckedBaseModel):
     Raw OCR data from the parsing process. Only included when `returnOcr` is configured in the parse config's advanced options.
     """
 
+    metadata: typing.Optional[ParseRunOutputMetadata] = pydantic.Field(default=None)
+    """
+    Rotation, dimension, and file-type metadata about the parse output. `null` for parse runs that completed before this field was introduced.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

src/extend_ai/types/parse_run_output_metadata.py

@@ -0,0 +1,44 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+import typing_extensions
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+from ..core.serialization import FieldMetadata
+from ..core.unchecked_base_model import UncheckedBaseModel
+from .parse_run_output_metadata_pages_item import ParseRunOutputMetadataPagesItem
+
+
+class ParseRunOutputMetadata(UncheckedBaseModel):
+    """
+    Rotation, dimension, and file-type metadata about the parse output. `null` for parse runs that completed before this field was introduced.
+    """
+
+    original_mime_type: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="originalMimeType")] = (
+        pydantic.Field(alias="originalMimeType", default=None)
+    )
+    """
+    The file's media type before any format conversion.
+    """
+
+    final_mime_type: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="finalMimeType")] = (
+        pydantic.Field(alias="finalMimeType", default=None)
+    )
+    """
+    The file's media type after any format conversion.
+    """
+
+    pages: typing.Optional[typing.List[ParseRunOutputMetadataPagesItem]] = pydantic.Field(default=None)
+    """
+    Per-page rotation and original-dimension info. Set when file is a PDF or was converted to PDF.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

src/extend_ai/types/parse_run_output_metadata_pages_item.py

@@ -0,0 +1,51 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+import typing_extensions
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+from ..core.serialization import FieldMetadata
+from ..core.unchecked_base_model import UncheckedBaseModel
+
+
+class ParseRunOutputMetadataPagesItem(UncheckedBaseModel):
+    number: int = pydantic.Field()
+    """
+    The page number this entry describes.
+    """
+
+    rotation_applied: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="rotationApplied")] = (
+        pydantic.Field(alias="rotationApplied", default=None)
+    )
+    """
+    Degrees Extend rotated the page clockwise to make it upright. `0` if rotation detection ran and the page was already upright; `null` if rotation detection was disabled for this run.
+    """
+
+    original_page_width: typing_extensions.Annotated[float, FieldMetadata(alias="originalPageWidth")] = pydantic.Field(
+        alias="originalPageWidth"
+    )
+    """
+    The file's true page width, independent of rendering resolution.
+    """
+
+    original_page_height: typing_extensions.Annotated[float, FieldMetadata(alias="originalPageHeight")] = (
+        pydantic.Field(alias="originalPageHeight")
+    )
+    """
+    The file's true page height, independent of rendering resolution.
+    """
+
+    dpi: float = pydantic.Field()
+    """
+    The DPI that `boundingBox`/`polygon` coordinates on this page are scaled to. Multiply `originalPageWidth`/`originalPageHeight` by `dpi / 72` to convert them into that same coordinate space.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

src/extend_ai/types/parse_run_output_ocr_words_item.py

@@ -35,6 +35,13 @@ class ParseRunOutputOcrWordsItem(UncheckedBaseModel):
     The page number where the word was detected.
     """
 
+    block_id: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="blockId")] = pydantic.Field(
+        alias="blockId", default=None
+    )
+    """
+    The `id` of the block (see the `Block` schema) this word was assigned to, based on bounding-box overlap. Omitted when the word doesn't fall within any block's bounding box.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

src/extend_ai/types/workflow_run_package.py

@@ -17,7 +17,7 @@ class WorkflowRunPackage(UncheckedBaseModel):
 
     files: typing.List[WorkflowRunPackageFilesItem] = pydantic.Field()
     """
-    The files to process, in submission order. Each entry can be a URL or an existing Extend file ID. Raw text and base64 inputs are not supported for package runs.
+    The files to process. Each entry can be a URL or an existing Extend file ID. Raw text and base64 inputs are not supported for package runs.
 
     Duplicate file IDs and duplicate URLs are rejected — each file may appear only once. A URL and a file ID are never treated as duplicates of each other, even if they resolve to the same document.
     """