chunkr-ai 0.1.0a7__py3-none-any.whl → 0.1.0a8__py3-none-any.whl

chunkr_ai/_utils/_utils.py

@@ -22,7 +22,6 @@ from typing_extensions import TypeGuard
 import sniffio
 
 from .._types import NotGiven, FileTypes, NotGivenOr, HeadersLike
-from .._compat import parse_date as parse_date, parse_datetime as parse_datetime
 
 _T = TypeVar("_T")
 _TupleT = TypeVar("_TupleT", bound=Tuple[object, ...])

chunkr_ai/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "chunkr_ai"
-__version__ = "0.1.0-alpha.7"  # x-release-please-version
+__version__ = "0.1.0-alpha.8"  # x-release-please-version

chunkr_ai/resources/tasks/extract.py

@@ -131,7 +131,6 @@ class ExtractResource(SyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -140,14 +139,10 @@ class ExtractResource(SyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> ExtractGetResponse:
         """
-        Retrieves the current state of an extract task and, when requested, can wait for
-        completion.
+        Retrieves the current state of an extract task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -161,8 +156,6 @@ class ExtractResource(SyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -184,7 +177,6 @@ class ExtractResource(SyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     extract_get_params.ExtractGetParams,
                 ),
@@ -299,7 +291,6 @@ class AsyncExtractResource(AsyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -308,14 +299,10 @@ class AsyncExtractResource(AsyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> ExtractGetResponse:
         """
-        Retrieves the current state of an extract task and, when requested, can wait for
-        completion.
+        Retrieves the current state of an extract task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -329,8 +316,6 @@ class AsyncExtractResource(AsyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -352,7 +337,6 @@ class AsyncExtractResource(AsyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     extract_get_params.ExtractGetParams,
                 ),

chunkr_ai/resources/tasks/parse.py

@@ -174,7 +174,6 @@ class ParseResource(SyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -183,14 +182,10 @@ class ParseResource(SyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> ParseGetResponse:
         """
-        Retrieves the current state of a parse task and, when requested, can wait for
-        completion.
+        Retrieves the current state of a parse task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -204,8 +199,6 @@ class ParseResource(SyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -227,7 +220,6 @@ class ParseResource(SyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     parse_get_params.ParseGetParams,
                 ),
@@ -382,7 +374,6 @@ class AsyncParseResource(AsyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -391,14 +382,10 @@ class AsyncParseResource(AsyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> ParseGetResponse:
         """
-        Retrieves the current state of a parse task and, when requested, can wait for
-        completion.
+        Retrieves the current state of a parse task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -412,8 +399,6 @@ class AsyncParseResource(AsyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -435,7 +420,6 @@ class AsyncParseResource(AsyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     parse_get_params.ParseGetParams,
                 ),

chunkr_ai/resources/tasks/tasks.py

@@ -240,7 +240,6 @@ class TasksResource(SyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -249,14 +248,10 @@ class TasksResource(SyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> TaskResponse:
         """
-        Retrieves the current state of a task and, when requested, can wait for
-        completion.
+        Retrieves the current state of a task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -270,8 +265,6 @@ class TasksResource(SyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -293,7 +286,6 @@ class TasksResource(SyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     task_get_params.TaskGetParams,
                 ),
@@ -500,7 +492,6 @@ class AsyncTasksResource(AsyncAPIResource):
         *,
         base64_urls: bool | NotGiven = NOT_GIVEN,
         include_chunks: bool | NotGiven = NOT_GIVEN,
-        wait_for_completion: bool | 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,
@@ -509,14 +500,10 @@ class AsyncTasksResource(AsyncAPIResource):
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
     ) -> TaskResponse:
         """
-        Retrieves the current state of a task and, when requested, can wait for
-        completion.
+        Retrieves the current state of a task.
 
         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.
+        available), file metadata, and timestamps.
 
         Typical uses:
 
@@ -530,8 +517,6 @@ class AsyncTasksResource(AsyncAPIResource):
 
           include_chunks: Whether to include chunks in the output response
 
-          wait_for_completion: Whether to wait for the task to complete
-
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -553,7 +538,6 @@ class AsyncTasksResource(AsyncAPIResource):
                     {
                         "base64_urls": base64_urls,
                         "include_chunks": include_chunks,
-                        "wait_for_completion": wait_for_completion,
                     },
                     task_get_params.TaskGetParams,
                 ),

chunkr_ai/types/extract_output_response.py

@@ -7,13 +7,56 @@ __all__ = ["ExtractOutputResponse"]
 
 class ExtractOutputResponse(BaseModel):
     citations: object
-    """Mirror of `results`; leaves are `Vec<Citation>` for the corresponding field"""
+    """Mirror of `results`; leaves are `Vec<Citation>` for the corresponding field
+
+    Example:
+
+    ```json
+    {
+      "field_name": [
+        {
+          "citation_id": "abc1234",
+          "citation_type": "Segment",
+          "bboxes": [
+            {
+              "left": 10,
+              "top": 20,
+              "width": 100,
+              "height": 18
+            }
+          ],
+          "content": "Example content",
+          "segment_id": "seg_001",
+          "segment_type": "Text",
+          "page_number": 1,
+          "page_height": 297,
+          "page_width": 210,
+          "ss_ranges": ["A1:C10"],
+          "ss_sheet_name": "Sheet1"
+        }
+      ]
+    }
+    ```
+    """
 
     metrics: object
     """
     Mirror of `results`; leaves contain a `Metrics` object for the corresponding
     field
+
+    Example:
+
+    ```json
+    { "field_name": { "confidence": "High" } }
+    ```
     """
 
     results: object
-    """JSON data that matches the provided schema"""
+    """JSON data that matches the provided schema
+
+    Example:
+
+    ```json
+    { "field_name": "value" }
+    ```
+    """

chunkr_ai/types/task_get_params.py

@@ -16,6 +16,3 @@ class TaskGetParams(TypedDict, total=False):
 
     include_chunks: bool
     """Whether to include chunks in the output response"""
-
-    wait_for_completion: bool
-    """Whether to wait for the task to complete"""

chunkr_ai/types/tasks/extract_create_response.py

@@ -55,153 +55,6 @@ class ExtractCreateResponse(BaseModel):
       array-of-primitives) contain a `Vec<Citation>` supporting that field.
     - `metrics`: mirror of `results`; only leaf positions contain a `Metrics` object
       for that field.
-
-    Detailed shape:
-
-    - Shared structure: `results`, `citations`, and `metrics` have the same
-      object/array shape as the user schema. Non-leaf nodes (objects, arrays of
-      objects) are mirrored; only leaves carry values.
-    - Leaf definition:
-      - A leaf is either a JSON primitive (string, number, bool, or null) or an
-        array of primitives (including empty).
-      - Arrays of objects are not leaves; recurse into their elements (`items`
-        mirror index-by-index).
-    - Null handling:
-      - If a leaf in `results` is null, the corresponding position in `citations`
-        and `metrics` remains null.
-    - Arrays:
-      - Array of objects: `citations`/`metrics` are arrays whose elements mirror
-        each object and carry values at their own leaves.
-      - Array of primitives: treated as a single leaf. `citations[path]` is a list
-        of `Citation` supporting the array as a whole. `metrics[path]` is a
-        `Metrics` object for the array as a whole.
-    - Citations leaves:
-      - Type: JSON array of `Citation` objects.
-      - Each `Citation` has: `citation_id: string`, `citation_type: Segment|Word`,
-        `bbox: BoundingBox[]`, `content: string`, `segment_id?: string`,
-        `segment_type: SegmentType`, `ss_range?: string[]`.
-        - Segment citation: represents a full parsed segment; `segment_id` set,
-          `bbox` has one entry (segment box), `content` is the segment text. If the
-          segment is from a spreadsheet, `ss_range` contains the table range
-          (single-element array) or the underlying cell refs if available.
-        - Word citation: represents selected OCR words within a segment;
-          `segment_id` is null, `bbox` has one entry per word, `content` is the
-          whitespace-joined text of those words; `segment_type` is `Text`. If OCR
-          words came from spreadsheet cells, `ss_range` lists those cell refs.
-    - Metrics leaves:
-      - Type: `Metrics` object with `confidence: "High" | "Low"`, indicating whether
-        citations sufficiently support the item.
-
-    Example:
-
-    results
-
-    ```json
-    {
-      "invoice_id": "INV-001",
-      "seller": { "name": "Acme" },
-      "line_items": [{ "sku": "A1", "qty": 2 }],
-      "tags": ["urgent", "paid"],
-      "notes": null
-    }
-    ```
-
-    citations
-
-    ```json
-    {
-      "invoice_id": [
-        {
-          "citation_id": "abc1234",
-          "citation_type": "Segment",
-          "bbox": [{ "left": 10, "top": 20, "width": 100, "height": 18 }],
-          "content": "Invoice INV-001",
-          "segment_id": "seg_001",
-          "segment_type": "Text",
-          "ss_range": ["A1:C10"]
-        },
-        {
-          "citation_id": "pqr2345",
-          "citation_type": "Word",
-          "bbox": [
-            { "left": 12, "top": 24, "width": 36, "height": 18 },
-            { "left": 52, "top": 24, "width": 48, "height": 18 }
-          ],
-          "content": "INV-001",
-          "segment_id": null,
-          "segment_type": "Text",
-          "ss_range": ["B3", "C3"]
-        }
-      ],
-      "seller": {
-        "name": [
-          {
-            "citation_id": "def5678",
-            "citation_type": "Word",
-            "bbox": [
-              { "left": 45, "top": 80, "width": 30, "height": 12 },
-              { "left": 80, "top": 80, "width": 40, "height": 12 }
-            ],
-            "content": "Acme",
-            "segment_id": null,
-            "segment_type": "Text"
-          }
-        ]
-      },
-      "line_items": [
-        {
-          "sku": [
-            {
-              "citation_id": "ghi9012",
-              "citation_type": "Segment",
-              "bbox": [{ "left": 12, "top": 140, "width": 60, "height": 16 }],
-              "content": "A1",
-              "segment_id": "seg_010",
-              "segment_type": "Text",
-              "ss_range": ["D5:E12"]
-            }
-          ],
-          "qty": [
-            {
-              "citation_id": "jkl3456",
-              "citation_type": "Word",
-              "bbox": [{ "left": 85, "top": 140, "width": 12, "height": 16 }],
-              "content": "2",
-              "segment_id": null,
-              "segment_type": "Text",
-              "ss_range": ["E12"]
-            }
-          ]
-        }
-      ],
-      "tags": [
-        {
-          "citation_id": "mno7890",
-          "citation_type": "Segment",
-          "bbox": [{ "left": 12, "top": 200, "width": 100, "height": 16 }],
-          "content": "urgent paid",
-          "segment_id": "seg_020",
-          "segment_type": "Text",
-          "ss_range": ["A20:C25"]
-        }
-      ],
-      "notes": null
-    }
-    ```
-
-    metrics
-
-    ```json
-    {
-      "invoice_id": { "confidence": "High" },
-      "seller": { "name": { "confidence": "Low" } },
-      "line_items": [
-        { "sku": { "confidence": "High" }, "qty": { "confidence": "High" } }
-      ],
-      "tags": { "confidence": "Low" },
-      "notes": null
-    }
-    ```
     """
 
     source_task_id: Optional[str] = None

chunkr_ai/types/tasks/extract_get_params.py

@@ -16,6 +16,3 @@ class ExtractGetParams(TypedDict, total=False):
 
     include_chunks: bool
     """Whether to include chunks in the output response"""
-
-    wait_for_completion: bool
-    """Whether to wait for the task to complete"""

chunkr_ai/types/tasks/extract_get_response.py

@@ -55,153 +55,6 @@ class ExtractGetResponse(BaseModel):
       array-of-primitives) contain a `Vec<Citation>` supporting that field.
     - `metrics`: mirror of `results`; only leaf positions contain a `Metrics` object
       for that field.
-
-    Detailed shape:
-
-    - Shared structure: `results`, `citations`, and `metrics` have the same
-      object/array shape as the user schema. Non-leaf nodes (objects, arrays of
-      objects) are mirrored; only leaves carry values.
-    - Leaf definition:
-      - A leaf is either a JSON primitive (string, number, bool, or null) or an
-        array of primitives (including empty).
-      - Arrays of objects are not leaves; recurse into their elements (`items`
-        mirror index-by-index).
-    - Null handling:
-      - If a leaf in `results` is null, the corresponding position in `citations`
-        and `metrics` remains null.
-    - Arrays:
-      - Array of objects: `citations`/`metrics` are arrays whose elements mirror
-        each object and carry values at their own leaves.
-      - Array of primitives: treated as a single leaf. `citations[path]` is a list
-        of `Citation` supporting the array as a whole. `metrics[path]` is a
-        `Metrics` object for the array as a whole.
-    - Citations leaves:
-      - Type: JSON array of `Citation` objects.
-      - Each `Citation` has: `citation_id: string`, `citation_type: Segment|Word`,
-        `bbox: BoundingBox[]`, `content: string`, `segment_id?: string`,
-        `segment_type: SegmentType`, `ss_range?: string[]`.
-        - Segment citation: represents a full parsed segment; `segment_id` set,
-          `bbox` has one entry (segment box), `content` is the segment text. If the
-          segment is from a spreadsheet, `ss_range` contains the table range
-          (single-element array) or the underlying cell refs if available.
-        - Word citation: represents selected OCR words within a segment;
-          `segment_id` is null, `bbox` has one entry per word, `content` is the
-          whitespace-joined text of those words; `segment_type` is `Text`. If OCR
-          words came from spreadsheet cells, `ss_range` lists those cell refs.
-    - Metrics leaves:
-      - Type: `Metrics` object with `confidence: "High" | "Low"`, indicating whether
-        citations sufficiently support the item.
-
-    Example:
-
-    results
-
-    ```json
-    {
-      "invoice_id": "INV-001",
-      "seller": { "name": "Acme" },
-      "line_items": [{ "sku": "A1", "qty": 2 }],
-      "tags": ["urgent", "paid"],
-      "notes": null
-    }
-    ```
-
-    citations
-
-    ```json
-    {
-      "invoice_id": [
-        {
-          "citation_id": "abc1234",
-          "citation_type": "Segment",
-          "bbox": [{ "left": 10, "top": 20, "width": 100, "height": 18 }],
-          "content": "Invoice INV-001",
-          "segment_id": "seg_001",
-          "segment_type": "Text",
-          "ss_range": ["A1:C10"]
-        },
-        {
-          "citation_id": "pqr2345",
-          "citation_type": "Word",
-          "bbox": [
-            { "left": 12, "top": 24, "width": 36, "height": 18 },
-            { "left": 52, "top": 24, "width": 48, "height": 18 }
-          ],
-          "content": "INV-001",
-          "segment_id": null,
-          "segment_type": "Text",
-          "ss_range": ["B3", "C3"]
-        }
-      ],
-      "seller": {
-        "name": [
-          {
-            "citation_id": "def5678",
-            "citation_type": "Word",
-            "bbox": [
-              { "left": 45, "top": 80, "width": 30, "height": 12 },
-              { "left": 80, "top": 80, "width": 40, "height": 12 }
-            ],
-            "content": "Acme",
-            "segment_id": null,
-            "segment_type": "Text"
-          }
-        ]
-      },
-      "line_items": [
-        {
-          "sku": [
-            {
-              "citation_id": "ghi9012",
-              "citation_type": "Segment",
-              "bbox": [{ "left": 12, "top": 140, "width": 60, "height": 16 }],
-              "content": "A1",
-              "segment_id": "seg_010",
-              "segment_type": "Text",
-              "ss_range": ["D5:E12"]
-            }
-          ],
-          "qty": [
-            {
-              "citation_id": "jkl3456",
-              "citation_type": "Word",
-              "bbox": [{ "left": 85, "top": 140, "width": 12, "height": 16 }],
-              "content": "2",
-              "segment_id": null,
-              "segment_type": "Text",
-              "ss_range": ["E12"]
-            }
-          ]
-        }
-      ],
-      "tags": [
-        {
-          "citation_id": "mno7890",
-          "citation_type": "Segment",
-          "bbox": [{ "left": 12, "top": 200, "width": 100, "height": 16 }],
-          "content": "urgent paid",
-          "segment_id": "seg_020",
-          "segment_type": "Text",
-          "ss_range": ["A20:C25"]
-        }
-      ],
-      "notes": null
-    }
-    ```
-
-    metrics
-
-    ```json
-    {
-      "invoice_id": { "confidence": "High" },
-      "seller": { "name": { "confidence": "Low" } },
-      "line_items": [
-        { "sku": { "confidence": "High" }, "qty": { "confidence": "High" } }
-      ],
-      "tags": { "confidence": "Low" },
-      "notes": null
-    }
-    ```
     """
 
     source_task_id: Optional[str] = None

chunkr_ai/types/tasks/parse_get_params.py

@@ -16,6 +16,3 @@ class ParseGetParams(TypedDict, total=False):
 
     include_chunks: bool
     """Whether to include chunks in the output response"""
-
-    wait_for_completion: bool
-    """Whether to wait for the task to complete"""

{chunkr_ai-0.1.0a7.dist-info → chunkr_ai-0.1.0a8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: chunkr-ai
-Version: 0.1.0a7
+Version: 0.1.0a8
 Summary: The official Python library for the chunkr API
 Project-URL: Homepage, https://github.com/lumina-ai-inc/chunkr-python
 Project-URL: Repository, https://github.com/lumina-ai-inc/chunkr-python