chunkr-ai 0.1.0a5__py3-none-any.whl → 0.1.0a7__py3-none-any.whl

chunkr_ai/resources/tasks/parse.py

@@ -17,9 +17,13 @@ from ..._response import (
     async_to_raw_response_wrapper,
     async_to_streamed_response_wrapper,
 )
-from ...types.task import Task
-from ...types.tasks import parse_create_params, parse_update_params
+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
+from ...types.tasks.parse_create_response import ParseCreateResponse
 
 __all__ = ["ParseResource", "AsyncParseResource"]
 
@@ -48,18 +52,15 @@ class ParseResource(SyncAPIResource):
         self,
         *,
         file: str,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | NotGiven = NOT_GIVEN,
-        chunk_processing: Optional[parse_create_params.ChunkProcessing] | NotGiven = NOT_GIVEN,
-        error_handling: Optional[Literal["Fail", "Continue"]] | NotGiven = NOT_GIVEN,
+        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: Optional[parse_create_params.LlmProcessing] | NotGiven = NOT_GIVEN,
-        ocr_strategy: Optional[Literal["All", "Auto"]] | NotGiven = NOT_GIVEN,
-        pipeline: Optional[Literal["Azure", "Chunkr"]] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[parse_create_params.SegmentProcessing] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]] | 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,
         # 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,
@@ -67,33 +68,23 @@ class ParseResource(SyncAPIResource):
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
         idempotency_key: str | None = None,
-    ) -> Task:
+    ) -> ParseCreateResponse:
         """
         Queues a document for processing and returns a `TaskResponse` with the assigned
         `task_id`, initial configuration, file metadata, and timestamps. The initial
         status is `Starting`.
 
-        If `wait_for_completion=true` is provided, the server waits briefly for
-        completion. If the task completes within that window, a 200 response with the
-        final `TaskResponse` is returned. Otherwise, the server returns a 408 or 409
-        with retry guidance and a body describing how long to wait before retrying.
+        Creates a parse task and returns its metadata immediately.
 
         Args:
           file:
-              The file to be uploaded. Supported inputs:
+              The file to be parsed. Supported inputs:
 
               - `ch://files/{file_id}`: Reference to an existing file. Upload via the Files
                 API
               - `http(s)://...`: Remote URL to fetch
               - `data:*;base64,...` or raw base64 string
 
-          base64_urls: Whether to return base64 encoded URLs. If false, presigned URLs are returned.
-
-          include_chunks: Whether to include chunks in the output response
-
-          wait_for_completion: If true, server holds briefly and may return 200 when done; otherwise returns
-              408/409 with Retry-After headers
-
           chunk_processing: Controls the setting for the chunking and post-processing of each chunk.
 
           error_handling:
@@ -106,7 +97,7 @@ class ParseResource(SyncAPIResource):
           expires_in: The number of seconds until task is deleted. Expired tasks can **not** be
               updated, polled or accessed via web interface.
 
-          file_name: The name of the file to be uploaded. If not set a name will be generated.
+          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.
 
@@ -117,41 +108,26 @@ class ParseResource(SyncAPIResource):
                 text. When text layer is present the bounding boxes from the text layer are
                 used.
 
-          pipeline: Choose the provider whose models will be used for segmentation and OCR. The
-              output will be unified to the Chunkr `output` format.
-
-          segment_processing: Defines how each segment type is handled when generating the final output.
-
-              Each segment uses one of three strategies. The chosen strategy controls:
-
-              - Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`).
-              - How the content is produced (rule-based vs. LLM).
-              - The output format (`Html` or `Markdown`).
+          segment_processing: Configuration for how each document segment is processed and formatted.
 
-              Optional flags such as image **cropping**, **extended context**, and
-              **descriptions** further refine behaviour.
+              Each segment has sensible defaults, but you can override specific settings:
 
-              **Default strategy per segment**
+              - `format`: Output as `Html` or `Markdown`
+              - `strategy`: `Auto` (rule-based), `LLM` (AI-generated), or `Ignore` (skip)
+              - `crop_image`: Whether to crop images to segment bounds
+              - `extended_context`: Use full page as context for LLM processing
+              - `description`: Generate descriptions for segments
 
-              - `Title`, `SectionHeader`, `Text`, `ListItem`, `Caption`, `Footnote` → **Auto**
-                (Markdown, description off)
-              - `Table` → **LLM** (HTML, description on)
-              - `Picture` → **LLM** (Markdown, description off, cropping _All_)
-              - `Formula`, `Page` → **LLM** (Markdown, description off)
-              - `PageHeader`, `PageFooter` → **Ignore** (removed from output)
+              **Defaults per segment type:** Check the documentation for more details.
 
-              **Strategy reference**
-
-              - **Auto** – rule-based content generation.
-              - **LLM** – generate content with an LLM.
-              - **Ignore** – exclude the segment entirely.
+              Only specify the fields you want to change - everything else uses the defaults.
 
           segmentation_strategy:
               Controls the segmentation strategy:
 
               - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
                 `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-                segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
+                segmentation and better chunking.
               - `Page`: Treats each page as a single segment. Faster processing, but without
                 layout element detection and only simple chunking.
 
@@ -188,126 +164,47 @@ class ParseResource(SyncAPIResource):
                 extra_body=extra_body,
                 timeout=timeout,
                 idempotency_key=idempotency_key,
-                query=maybe_transform(
-                    {
-                        "base64_urls": base64_urls,
-                        "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
-                    },
-                    parse_create_params.ParseCreateParams,
-                ),
             ),
-            cast_to=Task,
+            cast_to=ParseCreateResponse,
         )
 
-    def update(
+    def get(
         self,
-        task_id: str,
+        task_id: Optional[str],
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
         wait_for_completion: bool | NotGiven = NOT_GIVEN,
-        chunk_processing: Optional[parse_update_params.ChunkProcessing] | NotGiven = NOT_GIVEN,
-        error_handling: Optional[Literal["Fail", "Continue"]] | NotGiven = NOT_GIVEN,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        high_resolution: Optional[bool] | NotGiven = NOT_GIVEN,
-        llm_processing: Optional[parse_update_params.LlmProcessing] | NotGiven = NOT_GIVEN,
-        ocr_strategy: Optional[Literal["All", "Auto"]] | NotGiven = NOT_GIVEN,
-        pipeline: Optional[Literal["Azure", "Chunkr"]] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[parse_update_params.SegmentProcessing] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]] | NotGiven = NOT_GIVEN,
         # 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,
-        idempotency_key: str | None = None,
-    ) -> Task:
-        """Updates an existing task's configuration and reprocesses the document.
-
-        The
-        current configuration is used as the base; only provided fields are changed.
+    ) -> ParseGetResponse:
+        """
+        Retrieves the current state of a parse task and, when requested, can wait for
+        completion.
 
-        Requirements:
+        Returns task details such as processing status, configuration, output (when
+        available), file metadata, and timestamps. If `wait_for_completion=true` is
+        provided, the server will hold the request briefly. If the task does not reach a
+        terminal state during that window, the response will indicate a retry with
+        appropriate headers.
 
-        - Task must be in a terminal state (`Succeeded` or `Failed`).
-        - The new configuration must differ from the current configuration.
+        Typical uses:
 
-        If `wait_for_completion=true` is provided, the server waits briefly for
-        completion. If the task completes within that window, a 200 response with the
-        final `TaskResponse` is returned. Otherwise, the server returns a 408 with retry
-        guidance and a body describing how long to wait before retrying.
+        - Poll a task during processing
+        - Retrieve the final output once processing is complete
+        - Access task metadata and configuration
 
         Args:
-          base64_urls: Whether to return base64 encoded URLs. If false, presigned URLs are returned.
+          base64_urls: Whether to return base64 encoded URLs. If false, the URLs will be returned as
+              presigned URLs.
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: If true, server holds briefly and may return 200 when done; otherwise returns
-              408/409 with Retry-After headers
-
-          chunk_processing: Controls the setting for the chunking and post-processing of each chunk.
-
-          error_handling:
-              Controls how errors are handled during processing:
-
-              - `Fail`: Stops processing and fails the task when any error occurs
-              - `Continue`: Attempts to continue processing despite non-critical errors (eg.
-                LLM refusals etc.)
-
-          expires_in: The number of seconds until task is deleted. Expired tasks can **not** be
-              updated, polled or accessed via web interface.
-
-          high_resolution: Whether to use high-resolution images for cropping and post-processing. (Latency
-              penalty: ~7 seconds per page)
-
-          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)
-              - `Auto`: Selectively applies OCR only to pages with missing or low-quality
-                text. When text layer is present the bounding boxes from the text layer are
-                used.
-
-          pipeline: Choose the provider whose models will be used for segmentation and OCR. The
-              output will be unified to the Chunkr `output` format.
-
-          segment_processing: Defines how each segment type is handled when generating the final output.
-
-              Each segment uses one of three strategies. The chosen strategy controls:
-
-              - Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`).
-              - How the content is produced (rule-based vs. LLM).
-              - The output format (`Html` or `Markdown`).
-
-              Optional flags such as image **cropping**, **extended context**, and
-              **descriptions** further refine behaviour.
-
-              **Default strategy per segment**
-
-              - `Title`, `SectionHeader`, `Text`, `ListItem`, `Caption`, `Footnote` → **Auto**
-                (Markdown, description off)
-              - `Table` → **LLM** (HTML, description on)
-              - `Picture` → **LLM** (Markdown, description off, cropping _All_)
-              - `Formula`, `Page` → **LLM** (Markdown, description off)
-              - `PageHeader`, `PageFooter` → **Ignore** (removed from output)
-
-              **Strategy reference**
-
-              - **Auto** – rule-based content generation.
-              - **LLM** – generate content with an LLM.
-              - **Ignore** – exclude the segment entirely.
-
-          segmentation_strategy:
-              Controls the segmentation strategy:
-
-              - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
-                `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-                segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
-              - `Page`: Treats each page as a single segment. Faster processing, but without
-                layout element detection and only simple chunking.
+          wait_for_completion: Whether to wait for the task to complete
 
           extra_headers: Send extra headers
 
@@ -316,43 +213,26 @@ class ParseResource(SyncAPIResource):
           extra_body: Add additional JSON properties to the request
 
           timeout: Override the client-level default timeout for this request, in seconds
-
-          idempotency_key: Specify a custom idempotency key for this request
         """
         if not task_id:
             raise ValueError(f"Expected a non-empty value for `task_id` but received {task_id!r}")
-        return self._patch(
-            f"/tasks/parse/{task_id}",
-            body=maybe_transform(
-                {
-                    "chunk_processing": chunk_processing,
-                    "error_handling": error_handling,
-                    "expires_in": expires_in,
-                    "high_resolution": high_resolution,
-                    "llm_processing": llm_processing,
-                    "ocr_strategy": ocr_strategy,
-                    "pipeline": pipeline,
-                    "segment_processing": segment_processing,
-                    "segmentation_strategy": segmentation_strategy,
-                },
-                parse_update_params.ParseUpdateParams,
-            ),
+        return self._get(
+            f"/tasks/{task_id}/parse",
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
                 extra_body=extra_body,
                 timeout=timeout,
-                idempotency_key=idempotency_key,
                 query=maybe_transform(
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
                         "wait_for_completion": wait_for_completion,
                     },
-                    parse_update_params.ParseUpdateParams,
+                    parse_get_params.ParseGetParams,
                 ),
             ),
-            cast_to=Task,
+            cast_to=ParseGetResponse,
         )
 
 
@@ -380,18 +260,15 @@ class AsyncParseResource(AsyncAPIResource):
         self,
         *,
         file: str,
-        base64_urls: bool | NotGiven = NOT_GIVEN,
-        include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | NotGiven = NOT_GIVEN,
-        chunk_processing: Optional[parse_create_params.ChunkProcessing] | NotGiven = NOT_GIVEN,
-        error_handling: Optional[Literal["Fail", "Continue"]] | NotGiven = NOT_GIVEN,
+        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: Optional[parse_create_params.LlmProcessing] | NotGiven = NOT_GIVEN,
-        ocr_strategy: Optional[Literal["All", "Auto"]] | NotGiven = NOT_GIVEN,
-        pipeline: Optional[Literal["Azure", "Chunkr"]] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[parse_create_params.SegmentProcessing] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]] | 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,
         # 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,
@@ -399,33 +276,23 @@ class AsyncParseResource(AsyncAPIResource):
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
         idempotency_key: str | None = None,
-    ) -> Task:
+    ) -> ParseCreateResponse:
         """
         Queues a document for processing and returns a `TaskResponse` with the assigned
         `task_id`, initial configuration, file metadata, and timestamps. The initial
         status is `Starting`.
 
-        If `wait_for_completion=true` is provided, the server waits briefly for
-        completion. If the task completes within that window, a 200 response with the
-        final `TaskResponse` is returned. Otherwise, the server returns a 408 or 409
-        with retry guidance and a body describing how long to wait before retrying.
+        Creates a parse task and returns its metadata immediately.
 
         Args:
           file:
-              The file to be uploaded. Supported inputs:
+              The file to be parsed. Supported inputs:
 
               - `ch://files/{file_id}`: Reference to an existing file. Upload via the Files
                 API
               - `http(s)://...`: Remote URL to fetch
               - `data:*;base64,...` or raw base64 string
 
-          base64_urls: Whether to return base64 encoded URLs. If false, presigned URLs are returned.
-
-          include_chunks: Whether to include chunks in the output response
-
-          wait_for_completion: If true, server holds briefly and may return 200 when done; otherwise returns
-              408/409 with Retry-After headers
-
           chunk_processing: Controls the setting for the chunking and post-processing of each chunk.
 
           error_handling:
@@ -438,7 +305,7 @@ class AsyncParseResource(AsyncAPIResource):
           expires_in: The number of seconds until task is deleted. Expired tasks can **not** be
               updated, polled or accessed via web interface.
 
-          file_name: The name of the file to be uploaded. If not set a name will be generated.
+          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.
 
@@ -449,41 +316,26 @@ class AsyncParseResource(AsyncAPIResource):
                 text. When text layer is present the bounding boxes from the text layer are
                 used.
 
-          pipeline: Choose the provider whose models will be used for segmentation and OCR. The
-              output will be unified to the Chunkr `output` format.
-
-          segment_processing: Defines how each segment type is handled when generating the final output.
-
-              Each segment uses one of three strategies. The chosen strategy controls:
-
-              - Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`).
-              - How the content is produced (rule-based vs. LLM).
-              - The output format (`Html` or `Markdown`).
+          segment_processing: Configuration for how each document segment is processed and formatted.
 
-              Optional flags such as image **cropping**, **extended context**, and
-              **descriptions** further refine behaviour.
+              Each segment has sensible defaults, but you can override specific settings:
 
-              **Default strategy per segment**
+              - `format`: Output as `Html` or `Markdown`
+              - `strategy`: `Auto` (rule-based), `LLM` (AI-generated), or `Ignore` (skip)
+              - `crop_image`: Whether to crop images to segment bounds
+              - `extended_context`: Use full page as context for LLM processing
+              - `description`: Generate descriptions for segments
 
-              - `Title`, `SectionHeader`, `Text`, `ListItem`, `Caption`, `Footnote` → **Auto**
-                (Markdown, description off)
-              - `Table` → **LLM** (HTML, description on)
-              - `Picture` → **LLM** (Markdown, description off, cropping _All_)
-              - `Formula`, `Page` → **LLM** (Markdown, description off)
-              - `PageHeader`, `PageFooter` → **Ignore** (removed from output)
+              **Defaults per segment type:** Check the documentation for more details.
 
-              **Strategy reference**
-
-              - **Auto** – rule-based content generation.
-              - **LLM** – generate content with an LLM.
-              - **Ignore** – exclude the segment entirely.
+              Only specify the fields you want to change - everything else uses the defaults.
 
           segmentation_strategy:
               Controls the segmentation strategy:
 
               - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
                 `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-                segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
+                segmentation and better chunking.
               - `Page`: Treats each page as a single segment. Faster processing, but without
                 layout element detection and only simple chunking.
 
@@ -520,126 +372,47 @@ class AsyncParseResource(AsyncAPIResource):
                 extra_body=extra_body,
                 timeout=timeout,
                 idempotency_key=idempotency_key,
-                query=await async_maybe_transform(
-                    {
-                        "base64_urls": base64_urls,
-                        "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
-                    },
-                    parse_create_params.ParseCreateParams,
-                ),
             ),
-            cast_to=Task,
+            cast_to=ParseCreateResponse,
         )
 
-    async def update(
+    async def get(
         self,
-        task_id: str,
+        task_id: Optional[str],
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
         wait_for_completion: bool | NotGiven = NOT_GIVEN,
-        chunk_processing: Optional[parse_update_params.ChunkProcessing] | NotGiven = NOT_GIVEN,
-        error_handling: Optional[Literal["Fail", "Continue"]] | NotGiven = NOT_GIVEN,
-        expires_in: Optional[int] | NotGiven = NOT_GIVEN,
-        high_resolution: Optional[bool] | NotGiven = NOT_GIVEN,
-        llm_processing: Optional[parse_update_params.LlmProcessing] | NotGiven = NOT_GIVEN,
-        ocr_strategy: Optional[Literal["All", "Auto"]] | NotGiven = NOT_GIVEN,
-        pipeline: Optional[Literal["Azure", "Chunkr"]] | NotGiven = NOT_GIVEN,
-        segment_processing: Optional[parse_update_params.SegmentProcessing] | NotGiven = NOT_GIVEN,
-        segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]] | NotGiven = NOT_GIVEN,
         # 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,
-        idempotency_key: str | None = None,
-    ) -> Task:
-        """Updates an existing task's configuration and reprocesses the document.
-
-        The
-        current configuration is used as the base; only provided fields are changed.
+    ) -> ParseGetResponse:
+        """
+        Retrieves the current state of a parse task and, when requested, can wait for
+        completion.
 
-        Requirements:
+        Returns task details such as processing status, configuration, output (when
+        available), file metadata, and timestamps. If `wait_for_completion=true` is
+        provided, the server will hold the request briefly. If the task does not reach a
+        terminal state during that window, the response will indicate a retry with
+        appropriate headers.
 
-        - Task must be in a terminal state (`Succeeded` or `Failed`).
-        - The new configuration must differ from the current configuration.
+        Typical uses:
 
-        If `wait_for_completion=true` is provided, the server waits briefly for
-        completion. If the task completes within that window, a 200 response with the
-        final `TaskResponse` is returned. Otherwise, the server returns a 408 with retry
-        guidance and a body describing how long to wait before retrying.
+        - Poll a task during processing
+        - Retrieve the final output once processing is complete
+        - Access task metadata and configuration
 
         Args:
-          base64_urls: Whether to return base64 encoded URLs. If false, presigned URLs are returned.
+          base64_urls: Whether to return base64 encoded URLs. If false, the URLs will be returned as
+              presigned URLs.
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: If true, server holds briefly and may return 200 when done; otherwise returns
-              408/409 with Retry-After headers
-
-          chunk_processing: Controls the setting for the chunking and post-processing of each chunk.
-
-          error_handling:
-              Controls how errors are handled during processing:
-
-              - `Fail`: Stops processing and fails the task when any error occurs
-              - `Continue`: Attempts to continue processing despite non-critical errors (eg.
-                LLM refusals etc.)
-
-          expires_in: The number of seconds until task is deleted. Expired tasks can **not** be
-              updated, polled or accessed via web interface.
-
-          high_resolution: Whether to use high-resolution images for cropping and post-processing. (Latency
-              penalty: ~7 seconds per page)
-
-          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)
-              - `Auto`: Selectively applies OCR only to pages with missing or low-quality
-                text. When text layer is present the bounding boxes from the text layer are
-                used.
-
-          pipeline: Choose the provider whose models will be used for segmentation and OCR. The
-              output will be unified to the Chunkr `output` format.
-
-          segment_processing: Defines how each segment type is handled when generating the final output.
-
-              Each segment uses one of three strategies. The chosen strategy controls:
-
-              - Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`).
-              - How the content is produced (rule-based vs. LLM).
-              - The output format (`Html` or `Markdown`).
-
-              Optional flags such as image **cropping**, **extended context**, and
-              **descriptions** further refine behaviour.
-
-              **Default strategy per segment**
-
-              - `Title`, `SectionHeader`, `Text`, `ListItem`, `Caption`, `Footnote` → **Auto**
-                (Markdown, description off)
-              - `Table` → **LLM** (HTML, description on)
-              - `Picture` → **LLM** (Markdown, description off, cropping _All_)
-              - `Formula`, `Page` → **LLM** (Markdown, description off)
-              - `PageHeader`, `PageFooter` → **Ignore** (removed from output)
-
-              **Strategy reference**
-
-              - **Auto** – rule-based content generation.
-              - **LLM** – generate content with an LLM.
-              - **Ignore** – exclude the segment entirely.
-
-          segmentation_strategy:
-              Controls the segmentation strategy:
-
-              - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
-                `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-                segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
-              - `Page`: Treats each page as a single segment. Faster processing, but without
-                layout element detection and only simple chunking.
+          wait_for_completion: Whether to wait for the task to complete
 
           extra_headers: Send extra headers
 
@@ -648,43 +421,26 @@ class AsyncParseResource(AsyncAPIResource):
           extra_body: Add additional JSON properties to the request
 
           timeout: Override the client-level default timeout for this request, in seconds
-
-          idempotency_key: Specify a custom idempotency key for this request
         """
         if not task_id:
             raise ValueError(f"Expected a non-empty value for `task_id` but received {task_id!r}")
-        return await self._patch(
-            f"/tasks/parse/{task_id}",
-            body=await async_maybe_transform(
-                {
-                    "chunk_processing": chunk_processing,
-                    "error_handling": error_handling,
-                    "expires_in": expires_in,
-                    "high_resolution": high_resolution,
-                    "llm_processing": llm_processing,
-                    "ocr_strategy": ocr_strategy,
-                    "pipeline": pipeline,
-                    "segment_processing": segment_processing,
-                    "segmentation_strategy": segmentation_strategy,
-                },
-                parse_update_params.ParseUpdateParams,
-            ),
+        return await self._get(
+            f"/tasks/{task_id}/parse",
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
                 extra_body=extra_body,
                 timeout=timeout,
-                idempotency_key=idempotency_key,
                 query=await async_maybe_transform(
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
                         "wait_for_completion": wait_for_completion,
                     },
-                    parse_update_params.ParseUpdateParams,
+                    parse_get_params.ParseGetParams,
                 ),
             ),
-            cast_to=Task,
+            cast_to=ParseGetResponse,
         )
 
 
@@ -695,8 +451,8 @@ class ParseResourceWithRawResponse:
         self.create = to_raw_response_wrapper(
             parse.create,
         )
-        self.update = to_raw_response_wrapper(
-            parse.update,
+        self.get = to_raw_response_wrapper(
+            parse.get,
         )
 
 
@@ -707,8 +463,8 @@ class AsyncParseResourceWithRawResponse:
         self.create = async_to_raw_response_wrapper(
             parse.create,
         )
-        self.update = async_to_raw_response_wrapper(
-            parse.update,
+        self.get = async_to_raw_response_wrapper(
+            parse.get,
         )
 
 
@@ -719,8 +475,8 @@ class ParseResourceWithStreamingResponse:
         self.create = to_streamed_response_wrapper(
             parse.create,
         )
-        self.update = to_streamed_response_wrapper(
-            parse.update,
+        self.get = to_streamed_response_wrapper(
+            parse.get,
         )
 
 
@@ -731,6 +487,6 @@ class AsyncParseResourceWithStreamingResponse:
         self.create = async_to_streamed_response_wrapper(
             parse.create,
         )
-        self.update = async_to_streamed_response_wrapper(
-            parse.update,
+        self.get = async_to_streamed_response_wrapper(
+            parse.get,
         )