chunkr-ai 0.1.0a6__py3-none-any.whl → 0.1.0a8__py3-none-any.whl

chunkr_ai/types/segment_processing.py

@@ -0,0 +1,228 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+from .generation_config import GenerationConfig
+
+__all__ = ["SegmentProcessing"]
+
+
+class SegmentProcessing(BaseModel):
+    caption: Optional[GenerationConfig] = FieldInfo(alias="Caption", 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.
+    """
+
+    footnote: Optional[GenerationConfig] = FieldInfo(alias="Footnote", 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.
+
+    - `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.
+
+    - `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.
+    """
+
+    page: Optional[GenerationConfig] = FieldInfo(alias="Page", 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.
+    """
+
+    page_footer: Optional[GenerationConfig] = FieldInfo(alias="PageFooter", 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.
+    """
+
+    page_header: Optional[GenerationConfig] = FieldInfo(alias="PageHeader", 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.
+    """
+
+    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
+      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.
+    """
+
+    section_header: Optional[GenerationConfig] = FieldInfo(alias="SectionHeader", 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.
+    """
+
+    table: Optional[GenerationConfig] = FieldInfo(alias="Table", 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.
+    """
+
+    text: Optional[GenerationConfig] = FieldInfo(alias="Text", 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.
+    """
+
+    title: Optional[GenerationConfig] = FieldInfo(alias="Title", 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.
+    """

chunkr_ai/types/segment_processing_param.py

@@ -0,0 +1,229 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Annotated, TypedDict
+
+from .._utils import PropertyInfo
+from .generation_config_param import GenerationConfigParam
+
+__all__ = ["SegmentProcessingParam"]
+
+
+class SegmentProcessingParam(TypedDict, total=False):
+    caption: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Caption")]
+    """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.
+    """
+
+    footnote: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Footnote")]
+    """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: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Formula")]
+    """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: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="ListItem")]
+    """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.
+    """
+
+    page: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Page")]
+    """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.
+    """
+
+    page_footer: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="PageFooter")]
+    """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.
+    """
+
+    page_header: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="PageHeader")]
+    """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.
+    """
+
+    picture: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Picture")]
+    """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.
+    """
+
+    section_header: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="SectionHeader")]
+    """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.
+    """
+
+    table: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Table")]
+    """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.
+    """
+
+    text: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Text")]
+    """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.
+    """
+
+    title: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Title")]
+    """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.
+    """

chunkr_ai/types/task_extract_updated_webhook_event.py

@@ -0,0 +1,22 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["TaskExtractUpdatedWebhookEvent"]
+
+
+class TaskExtractUpdatedWebhookEvent(BaseModel):
+    event_type: Literal["task.parse.updated", "task.extract.updated"]
+    """Event type identifier"""
+
+    status: Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]
+    """Current status of the task"""
+
+    task_id: str
+    """Unique task identifier"""
+
+    message: Optional[str] = None
+    """Optional human-readable status message"""

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/task_list_params.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Union
+from typing import List, Union
 from datetime import datetime
 from typing_extensions import Literal, Annotated, TypedDict
 
@@ -35,3 +35,9 @@ class TaskListParams(TypedDict, total=False):
 
     start: Annotated[Union[str, datetime], PropertyInfo(format="iso8601")]
     """Start date"""
+
+    statuses: List[Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]]
+    """Filter by one or more statuses"""
+
+    task_types: List[Literal["Parse", "Extract"]]
+    """Filter by one or more task types"""

chunkr_ai/types/task_parse_updated_webhook_event.py

@@ -0,0 +1,22 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["TaskParseUpdatedWebhookEvent"]
+
+
+class TaskParseUpdatedWebhookEvent(BaseModel):
+    event_type: Literal["task.parse.updated", "task.extract.updated"]
+    """Event type identifier"""
+
+    status: Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]
+    """Current status of the task"""
+
+    task_id: str
+    """Unique task identifier"""
+
+    message: Optional[str] = None
+    """Optional human-readable status message"""

chunkr_ai/types/task_response.py

@@ -0,0 +1,68 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union, Optional
+from datetime import datetime
+from typing_extensions import Literal, TypeAlias
+
+from .._models import BaseModel
+from .file_info import FileInfo
+from .version_info import VersionInfo
+from .parse_configuration import ParseConfiguration
+from .extract_configuration import ExtractConfiguration
+from .parse_output_response import ParseOutputResponse
+from .extract_output_response import ExtractOutputResponse
+
+__all__ = ["TaskResponse", "Configuration", "Output"]
+
+Configuration: TypeAlias = Union[ParseConfiguration, ExtractConfiguration]
+
+Output: TypeAlias = Union[ParseOutputResponse, ExtractOutputResponse, None]
+
+
+class TaskResponse(BaseModel):
+    configuration: Configuration
+    """
+    Unified configuration type that can represent either parse or extract
+    configurations
+    """
+
+    created_at: datetime
+    """The date and time when the task was created and queued."""
+
+    file_info: FileInfo
+    """Information about the input file."""
+
+    message: str
+    """A message describing the task's status or any errors that occurred."""
+
+    status: Literal["Starting", "Processing", "Succeeded", "Failed", "Cancelled"]
+    """The status of the task."""
+
+    task_id: str
+    """The unique identifier for the task."""
+
+    task_type: Literal["Parse", "Extract"]
+
+    version_info: VersionInfo
+    """Version information for the task."""
+
+    expires_at: Optional[datetime] = None
+    """The date and time when the task will expire."""
+
+    finished_at: Optional[datetime] = None
+    """The date and time when the task was finished."""
+
+    input_file_url: Optional[str] = None
+    """The presigned URL of the input file. Deprecated use `file_info.url` instead."""
+
+    output: Optional[Output] = None
+    """Unified output type that can represent either parse or extract results"""
+
+    source_task_id: Optional[str] = None
+    """The ID of the source task that was used for the task"""
+
+    started_at: Optional[datetime] = None
+    """The date and time when the task was started."""
+
+    task_url: Optional[str] = None
+    """The presigned URL of the task."""

chunkr_ai/types/tasks/__init__.py

@@ -2,5 +2,11 @@
 
 from __future__ import annotations
 
+from .parse_get_params import ParseGetParams as ParseGetParams
+from .extract_get_params import ExtractGetParams as ExtractGetParams
+from .parse_get_response import ParseGetResponse as ParseGetResponse
 from .parse_create_params import ParseCreateParams as ParseCreateParams
-from .parse_update_params import ParseUpdateParams as ParseUpdateParams
+from .extract_get_response import ExtractGetResponse as ExtractGetResponse
+from .extract_create_params import ExtractCreateParams as ExtractCreateParams
+from .parse_create_response import ParseCreateResponse as ParseCreateResponse
+from .extract_create_response import ExtractCreateResponse as ExtractCreateResponse

chunkr_ai/types/tasks/extract_create_params.py

@@ -0,0 +1,47 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+from ..parse_configuration_param import ParseConfigurationParam
+
+__all__ = ["ExtractCreateParams"]
+
+
+class ExtractCreateParams(TypedDict, total=False):
+    file: Required[str]
+    """The file to be extracted. 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
+    - `task_id`: Reference to an existing `parse`task.
+    """
+
+    schema: Required[object]
+    """The schema to be used for the extraction."""
+
+    expires_in: Optional[int]
+    """
+    The number of seconds until task is deleted. Expired tasks can **not** be
+    updated, polled or accessed via web interface.
+    """
+
+    file_name: Optional[str]
+    """The name of the file to be extracted.
+
+    If not set a name will be generated. Can not be provided if the `file` is a
+    `task_id`.
+    """
+
+    parse_configuration: Optional[ParseConfigurationParam]
+    """
+    Optional configuration for the `parse` task. Can not be used if `file` is a
+    `task_id`.
+    """
+
+    system_prompt: Optional[str]
+    """The system prompt to be used for the extraction."""