chunkr-ai 0.1.0a8__py3-none-any.whl → 0.1.0a9__py3-none-any.whl

chunkr_ai/resources/tasks/extract.py

@@ -6,7 +6,7 @@ from typing import Optional
 
 import httpx
 
-from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ..._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
 from ..._utils import maybe_transform, async_maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
@@ -50,16 +50,16 @@ class ExtractResource(SyncAPIResource):
         *,
         file: str,
         schema: object,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        file_name: Optional[str] | NotGiven = NOT_GIVEN,
-        parse_configuration: Optional[ParseConfigurationParam] | NotGiven = NOT_GIVEN,
-        system_prompt: Optional[str] | NotGiven = NOT_GIVEN,
+        expires_in: Optional[int] | Omit = omit,
+        file_name: Optional[str] | Omit = omit,
+        parse_configuration: Optional[ParseConfigurationParam] | Omit = omit,
+        system_prompt: Optional[str] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> ExtractCreateResponse:
         """
@@ -129,14 +129,14 @@ class ExtractResource(SyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> ExtractGetResponse:
         """
         Retrieves the current state of an extract task.
@@ -210,16 +210,16 @@ class AsyncExtractResource(AsyncAPIResource):
         *,
         file: str,
         schema: object,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        file_name: Optional[str] | NotGiven = NOT_GIVEN,
-        parse_configuration: Optional[ParseConfigurationParam] | NotGiven = NOT_GIVEN,
-        system_prompt: Optional[str] | NotGiven = NOT_GIVEN,
+        expires_in: Optional[int] | Omit = omit,
+        file_name: Optional[str] | Omit = omit,
+        parse_configuration: Optional[ParseConfigurationParam] | Omit = omit,
+        system_prompt: Optional[str] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> ExtractCreateResponse:
         """
@@ -289,14 +289,14 @@ class AsyncExtractResource(AsyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> ExtractGetResponse:
         """
         Retrieves the current state of an extract task.

chunkr_ai/resources/tasks/parse.py

@@ -7,7 +7,7 @@ from typing_extensions import Literal
 
 import httpx
 
-from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from ..._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
 from ..._utils import maybe_transform, async_maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
@@ -19,7 +19,6 @@ from ..._response import (
 )
 from ...types.tasks import parse_get_params, parse_create_params
 from ..._base_client import make_request_options
-from ...types.llm_processing_param import LlmProcessingParam
 from ...types.chunk_processing_param import ChunkProcessingParam
 from ...types.segment_processing_param import SegmentProcessingParam
 from ...types.tasks.parse_get_response import ParseGetResponse
@@ -52,21 +51,20 @@ class ParseResource(SyncAPIResource):
         self,
         *,
         file: str,
-        chunk_processing: ChunkProcessingParam | NotGiven = NOT_GIVEN,
-        error_handling: Literal["Fail", "Continue"] | NotGiven = NOT_GIVEN,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        file_name: Optional[str] | NotGiven = NOT_GIVEN,
-        llm_processing: LlmProcessingParam | NotGiven = NOT_GIVEN,
-        ocr_strategy: Literal["All", "Auto"] | NotGiven = NOT_GIVEN,
-        pipeline: Literal["Azure", "Chunkr"] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[SegmentProcessingParam] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Literal["LayoutAnalysis", "Page"] | NotGiven = NOT_GIVEN,
+        chunk_processing: ChunkProcessingParam | Omit = omit,
+        error_handling: Literal["Fail", "Continue"] | Omit = omit,
+        expires_in: Optional[int] | Omit = omit,
+        file_name: Optional[str] | Omit = omit,
+        ocr_strategy: Literal["All", "Auto"] | Omit = omit,
+        pipeline: Literal["Azure", "Chunkr"] | Omit = omit,
+        segment_processing: Optional[SegmentProcessingParam] | Omit = omit,
+        segmentation_strategy: Literal["LayoutAnalysis", "Page"] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> ParseCreateResponse:
         """
@@ -99,8 +97,6 @@ class ParseResource(SyncAPIResource):
 
           file_name: The name of the file to be parsed. If not set a name will be generated.
 
-          llm_processing: Controls the LLM used for the task.
-
           ocr_strategy: Controls the Optical Character Recognition (OCR) strategy.
 
               - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
@@ -150,7 +146,6 @@ class ParseResource(SyncAPIResource):
                     "error_handling": error_handling,
                     "expires_in": expires_in,
                     "file_name": file_name,
-                    "llm_processing": llm_processing,
                     "ocr_strategy": ocr_strategy,
                     "pipeline": pipeline,
                     "segment_processing": segment_processing,
@@ -172,14 +167,14 @@ class ParseResource(SyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> ParseGetResponse:
         """
         Retrieves the current state of a parse task.
@@ -252,21 +247,20 @@ class AsyncParseResource(AsyncAPIResource):
         self,
         *,
         file: str,
-        chunk_processing: ChunkProcessingParam | NotGiven = NOT_GIVEN,
-        error_handling: Literal["Fail", "Continue"] | NotGiven = NOT_GIVEN,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        file_name: Optional[str] | NotGiven = NOT_GIVEN,
-        llm_processing: LlmProcessingParam | NotGiven = NOT_GIVEN,
-        ocr_strategy: Literal["All", "Auto"] | NotGiven = NOT_GIVEN,
-        pipeline: Literal["Azure", "Chunkr"] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[SegmentProcessingParam] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Literal["LayoutAnalysis", "Page"] | NotGiven = NOT_GIVEN,
+        chunk_processing: ChunkProcessingParam | Omit = omit,
+        error_handling: Literal["Fail", "Continue"] | Omit = omit,
+        expires_in: Optional[int] | Omit = omit,
+        file_name: Optional[str] | Omit = omit,
+        ocr_strategy: Literal["All", "Auto"] | Omit = omit,
+        pipeline: Literal["Azure", "Chunkr"] | Omit = omit,
+        segment_processing: Optional[SegmentProcessingParam] | Omit = omit,
+        segmentation_strategy: Literal["LayoutAnalysis", "Page"] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> ParseCreateResponse:
         """
@@ -299,8 +293,6 @@ class AsyncParseResource(AsyncAPIResource):
 
           file_name: The name of the file to be parsed. If not set a name will be generated.
 
-          llm_processing: Controls the LLM used for the task.
-
           ocr_strategy: Controls the Optical Character Recognition (OCR) strategy.
 
               - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
@@ -350,7 +342,6 @@ class AsyncParseResource(AsyncAPIResource):
                     "error_handling": error_handling,
                     "expires_in": expires_in,
                     "file_name": file_name,
-                    "llm_processing": llm_processing,
                     "ocr_strategy": ocr_strategy,
                     "pipeline": pipeline,
                     "segment_processing": segment_processing,
@@ -372,14 +363,14 @@ class AsyncParseResource(AsyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> ParseGetResponse:
         """
         Retrieves the current state of a parse task.

chunkr_ai/resources/tasks/tasks.py

@@ -25,7 +25,7 @@ from .extract import (
     ExtractResourceWithStreamingResponse,
     AsyncExtractResourceWithStreamingResponse,
 )
-from ..._types import NOT_GIVEN, Body, Query, Headers, NoneType, NotGiven
+from ..._types import Body, Omit, Query, Headers, NoneType, NotGiven, omit, not_given
 from ..._utils import maybe_transform, async_maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
@@ -73,21 +73,21 @@ class TasksResource(SyncAPIResource):
     def list(
         self,
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        cursor: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        end: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
-        limit: int | NotGiven = NOT_GIVEN,
-        sort: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
-        start: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        statuses: List[Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]] | NotGiven = NOT_GIVEN,
-        task_types: List[Literal["Parse", "Extract"]] | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        cursor: Union[str, datetime] | Omit = omit,
+        end: Union[str, datetime] | Omit = omit,
+        include_chunks: bool | Omit = omit,
+        limit: int | Omit = omit,
+        sort: Literal["asc", "desc"] | Omit = omit,
+        start: Union[str, datetime] | Omit = omit,
+        statuses: List[Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]] | Omit = omit,
+        task_types: List[Literal["Parse", "Extract"]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> SyncTasksPage[TaskResponse]:
         """
         Lists tasks for the authenticated user with cursor-based pagination and optional
@@ -157,7 +157,7 @@ class TasksResource(SyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> None:
         """
@@ -202,7 +202,7 @@ class TasksResource(SyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> None:
         """
         Cancel a task that hasn't started processing yet:
@@ -238,14 +238,14 @@ class TasksResource(SyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> TaskResponse:
         """
         Retrieves the current state of a task.
@@ -325,21 +325,21 @@ class AsyncTasksResource(AsyncAPIResource):
     def list(
         self,
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        cursor: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        end: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
-        limit: int | NotGiven = NOT_GIVEN,
-        sort: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
-        start: Union[str, datetime] | NotGiven = NOT_GIVEN,
-        statuses: List[Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]] | NotGiven = NOT_GIVEN,
-        task_types: List[Literal["Parse", "Extract"]] | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        cursor: Union[str, datetime] | Omit = omit,
+        end: Union[str, datetime] | Omit = omit,
+        include_chunks: bool | Omit = omit,
+        limit: int | Omit = omit,
+        sort: Literal["asc", "desc"] | Omit = omit,
+        start: Union[str, datetime] | Omit = omit,
+        statuses: List[Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]] | Omit = omit,
+        task_types: List[Literal["Parse", "Extract"]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> AsyncPaginator[TaskResponse, AsyncTasksPage[TaskResponse]]:
         """
         Lists tasks for the authenticated user with cursor-based pagination and optional
@@ -409,7 +409,7 @@ class AsyncTasksResource(AsyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
         idempotency_key: str | None = None,
     ) -> None:
         """
@@ -454,7 +454,7 @@ class AsyncTasksResource(AsyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> None:
         """
         Cancel a task that hasn't started processing yet:
@@ -490,14 +490,14 @@ class AsyncTasksResource(AsyncAPIResource):
         self,
         task_id: Optional[str],
         *,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
+        base64_urls: bool | Omit = omit,
+        include_chunks: bool | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> TaskResponse:
         """
         Retrieves the current state of a task.

chunkr_ai/resources/webhooks.py

@@ -7,7 +7,7 @@ from typing import Mapping, cast
 
 import httpx
 
-from .._types import NOT_GIVEN, Body, Query, Headers, NotGiven
+from .._types import Body, Query, Headers, NotGiven, not_given
 from .._compat import cached_property
 from .._models import construct_type
 from .._resource import SyncAPIResource, AsyncAPIResource
@@ -79,7 +79,7 @@ class WebhooksResource(SyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> WebhookURLResponse:
         """Get or create webhook for user and return dashboard URL"""
         return self._get(
@@ -145,7 +145,7 @@ class AsyncWebhooksResource(AsyncAPIResource):
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
-        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> WebhookURLResponse:
         """Get or create webhook for user and return dashboard URL"""
         return await self._get(

chunkr_ai/types/__init__.py

@@ -15,7 +15,6 @@ from .ocr_result import OcrResult as OcrResult
 from .bounding_box import BoundingBox as BoundingBox
 from .version_info import VersionInfo as VersionInfo
 from .task_response import TaskResponse as TaskResponse
-from .llm_processing import LlmProcessing as LlmProcessing
 from .file_url_params import FileURLParams as FileURLParams
 from .task_get_params import TaskGetParams as TaskGetParams
 from .chunk_processing import ChunkProcessing as ChunkProcessing
@@ -26,7 +25,6 @@ from .file_create_params import FileCreateParams as FileCreateParams
 from .segment_processing import SegmentProcessing as SegmentProcessing
 from .files_list_response import FilesListResponse as FilesListResponse
 from .parse_configuration import ParseConfiguration as ParseConfiguration
-from .llm_processing_param import LlmProcessingParam as LlmProcessingParam
 from .unwrap_webhook_event import UnwrapWebhookEvent as UnwrapWebhookEvent
 from .webhook_url_response import WebhookURLResponse as WebhookURLResponse
 from .extract_configuration import ExtractConfiguration as ExtractConfiguration

chunkr_ai/types/file_info.py

@@ -19,3 +19,6 @@ class FileInfo(BaseModel):
 
     page_count: Optional[int] = None
     """The number of pages in the file."""
+
+    ss_cell_count: Optional[int] = None
+    """The number of cells in the file. Only used for spreadsheets."""

chunkr_ai/types/ocr_result.py

@@ -15,14 +15,14 @@ class OcrResult(BaseModel):
     text: str
     """The recognized text of the OCR result."""
 
-    cell_ref: Optional[str] = None
-    """
-    Excel-style cell reference (e.g., "A1" or "A1:B2") when OCR originates from a
-    spreadsheet cell
-    """
-
     confidence: Optional[float] = None
     """The confidence score of the recognized text."""
 
     ocr_id: Optional[str] = None
     """The unique identifier for the OCR result."""
+
+    ss_cell_ref: Optional[str] = None
+    """
+    Excel-style cell reference (e.g., "A1" or "A1:B2") when OCR originates from a
+    spreadsheet cell
+    """

chunkr_ai/types/parse_configuration.py

@@ -4,7 +4,6 @@ from typing import Optional
 from typing_extensions import Literal
 
 from .._models import BaseModel
-from .llm_processing import LlmProcessing
 from .chunk_processing import ChunkProcessing
 from .segment_processing import SegmentProcessing
 
@@ -23,9 +22,6 @@ class ParseConfiguration(BaseModel):
       LLM refusals etc.)
     """
 
-    llm_processing: Optional[LlmProcessing] = None
-    """Controls the LLM used for the task."""
-
     ocr_strategy: Optional[Literal["All", "Auto"]] = None
     """Controls the Optical Character Recognition (OCR) strategy.
 

chunkr_ai/types/parse_configuration_param.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 from typing import Optional
 from typing_extensions import Literal, TypedDict
 
-from .llm_processing_param import LlmProcessingParam
 from .chunk_processing_param import ChunkProcessingParam
 from .segment_processing_param import SegmentProcessingParam
 
@@ -24,9 +23,6 @@ class ParseConfigurationParam(TypedDict, total=False):
       LLM refusals etc.)
     """
 
-    llm_processing: LlmProcessingParam
-    """Controls the LLM used for the task."""
-
     ocr_strategy: Literal["All", "Auto"]
     """Controls the Optical Character Recognition (OCR) strategy.
 

chunkr_ai/types/segment.py

@@ -31,20 +31,23 @@ class Segment(BaseModel):
         "Caption",
         "Footnote",
         "Formula",
+        "FormRegion",
+        "GraphicalItem",
+        "Legend",
+        "LineNumber",
         "ListItem",
         "Page",
         "PageFooter",
         "PageHeader",
+        "PageNumber",
         "Picture",
-        "SectionHeader",
         "Table",
         "Text",
         "Title",
+        "Unknown",
+        "SectionHeader",
     ]
-    """
-    All the possible types for a segment. Note: Different configurations will
-    produce different types. Please refer to the documentation for more information.
-    """
+    """All the possible types for a segment."""
 
     confidence: Optional[float] = None
     """Confidence score of the layout analysis model"""

chunkr_ai/types/segment_processing.py

@@ -47,6 +47,24 @@ class SegmentProcessing(BaseModel):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
+    form_region: Optional[GenerationConfig] = FieldInfo(alias="FormRegion", default=None)
+    """Controls the processing and generation for the segment.
+
+    - `crop_image` controls whether to crop the file's images to the segment's
+      bounding box. The cropped image will be stored in the segment's `image` field.
+      Use `All` to always crop, or `Auto` to only crop when needed for
+      post-processing.
+    - `format` specifies the output format: `Html` or `Markdown`
+    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
+      - `Auto`: Process content automatically
+      - `LLM`: Use large language models for processing
+      - `Ignore`: Exclude segments from final output
+    - `description` enables LLM-generated descriptions for segments. **Note:** This
+      uses chunkr's own VLM models and is not configurable via LLM processing
+      configuration.
+    - `extended_context` uses the full page image as context for LLM generation.
+    """
+
     formula: Optional[GenerationConfig] = FieldInfo(alias="Formula", default=None)
     """Controls the processing and generation for the segment.
 
@@ -65,6 +83,60 @@ class SegmentProcessing(BaseModel):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
+    graphical_item: Optional[GenerationConfig] = FieldInfo(alias="GraphicalItem", default=None)
+    """Controls the processing and generation for the segment.
+
+    - `crop_image` controls whether to crop the file's images to the segment's
+      bounding box. The cropped image will be stored in the segment's `image` field.
+      Use `All` to always crop, or `Auto` to only crop when needed for
+      post-processing.
+    - `format` specifies the output format: `Html` or `Markdown`
+    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
+      - `Auto`: Process content automatically
+      - `LLM`: Use large language models for processing
+      - `Ignore`: Exclude segments from final output
+    - `description` enables LLM-generated descriptions for segments. **Note:** This
+      uses chunkr's own VLM models and is not configurable via LLM processing
+      configuration.
+    - `extended_context` uses the full page image as context for LLM generation.
+    """
+
+    legend: Optional[GenerationConfig] = FieldInfo(alias="Legend", default=None)
+    """Controls the processing and generation for the segment.
+
+    - `crop_image` controls whether to crop the file's images to the segment's
+      bounding box. The cropped image will be stored in the segment's `image` field.
+      Use `All` to always crop, or `Auto` to only crop when needed for
+      post-processing.
+    - `format` specifies the output format: `Html` or `Markdown`
+    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
+      - `Auto`: Process content automatically
+      - `LLM`: Use large language models for processing
+      - `Ignore`: Exclude segments from final output
+    - `description` enables LLM-generated descriptions for segments. **Note:** This
+      uses chunkr's own VLM models and is not configurable via LLM processing
+      configuration.
+    - `extended_context` uses the full page image as context for LLM generation.
+    """
+
+    line_number: Optional[GenerationConfig] = FieldInfo(alias="LineNumber", default=None)
+    """Controls the processing and generation for the segment.
+
+    - `crop_image` controls whether to crop the file's images to the segment's
+      bounding box. The cropped image will be stored in the segment's `image` field.
+      Use `All` to always crop, or `Auto` to only crop when needed for
+      post-processing.
+    - `format` specifies the output format: `Html` or `Markdown`
+    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
+      - `Auto`: Process content automatically
+      - `LLM`: Use large language models for processing
+      - `Ignore`: Exclude segments from final output
+    - `description` enables LLM-generated descriptions for segments. **Note:** This
+      uses chunkr's own VLM models and is not configurable via LLM processing
+      configuration.
+    - `extended_context` uses the full page image as context for LLM generation.
+    """
+
     list_item: Optional[GenerationConfig] = FieldInfo(alias="ListItem", default=None)
     """Controls the processing and generation for the segment.
 
@@ -137,7 +209,7 @@ class SegmentProcessing(BaseModel):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    picture: Optional[GenerationConfig] = FieldInfo(alias="Picture", default=None)
+    page_number: Optional[GenerationConfig] = FieldInfo(alias="PageNumber", default=None)
     """Controls the processing and generation for the segment.
 
     - `crop_image` controls whether to crop the file's images to the segment's
@@ -155,7 +227,7 @@ class SegmentProcessing(BaseModel):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    section_header: Optional[GenerationConfig] = FieldInfo(alias="SectionHeader", default=None)
+    picture: Optional[GenerationConfig] = FieldInfo(alias="Picture", default=None)
     """Controls the processing and generation for the segment.
 
     - `crop_image` controls whether to crop the file's images to the segment's
@@ -226,3 +298,21 @@ class SegmentProcessing(BaseModel):
       configuration.
     - `extended_context` uses the full page image as context for LLM generation.
     """
+
+    unknown: Optional[GenerationConfig] = FieldInfo(alias="Unknown", default=None)
+    """Controls the processing and generation for the segment.
+
+    - `crop_image` controls whether to crop the file's images to the segment's
+      bounding box. The cropped image will be stored in the segment's `image` field.
+      Use `All` to always crop, or `Auto` to only crop when needed for
+      post-processing.
+    - `format` specifies the output format: `Html` or `Markdown`
+    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
+      - `Auto`: Process content automatically
+      - `LLM`: Use large language models for processing
+      - `Ignore`: Exclude segments from final output
+    - `description` enables LLM-generated descriptions for segments. **Note:** This
+      uses chunkr's own VLM models and is not configurable via LLM processing
+      configuration.
+    - `extended_context` uses the full page image as context for LLM generation.
+    """