chunkr-ai 0.1.0a10__tar.gz → 0.1.0a11__tar.gz

chunkr_ai-0.1.0a11/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "0.1.0-alpha.11"
+}

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.1.0-alpha.11 (2025-10-02)
+
+Full Changelog: [v0.1.0-alpha.10...v0.1.0-alpha.11](https://github.com/lumina-ai-inc/chunkr-python/compare/v0.1.0-alpha.10...v0.1.0-alpha.11)
+
+### Features
+
+* **api:** api update ([335fcdd](https://github.com/lumina-ai-inc/chunkr-python/commit/335fcdd892d4d009ea966d12c5a3357fa38b595f))
+
 ## 0.1.0-alpha.10 (2025-10-02)
 
 Full Changelog: [v0.1.0-alpha.9...v0.1.0-alpha.10](https://github.com/lumina-ai-inc/chunkr-python/compare/v0.1.0-alpha.9...v0.1.0-alpha.10)

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: chunkr-ai
-Version: 0.1.0a10
+Version: 0.1.0a11
 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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "chunkr-ai"
-version = "0.1.0-alpha.10"
+version = "0.1.0-alpha.11"
 description = "The official Python library for the chunkr API"
 dynamic = ["readme"]
 license = "Apache-2.0"

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/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.10"  # x-release-please-version
+__version__ = "0.1.0-alpha.11"  # x-release-please-version

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/resources/tasks/parse.py

@@ -19,6 +19,7 @@ from ..._response import (
 )
 from ...types.tasks import parse_get_params, parse_create_params
 from ..._base_client import make_request_options
+from ...types.llm_processing_param import LlmProcessingParam
 from ...types.chunk_processing_param import ChunkProcessingParam
 from ...types.segment_processing_param import SegmentProcessingParam
 from ...types.tasks.parse_get_response import ParseGetResponse
@@ -55,6 +56,7 @@ class ParseResource(SyncAPIResource):
         error_handling: Literal["Fail", "Continue"] | Omit = omit,
         expires_in: Optional[int] | Omit = omit,
         file_name: Optional[str] | Omit = omit,
+        llm_processing: LlmProcessingParam | Omit = omit,
         ocr_strategy: Literal["All", "Auto"] | Omit = omit,
         pipeline: Literal["Azure", "Chunkr"] | Omit = omit,
         segment_processing: Optional[SegmentProcessingParam] | Omit = omit,
@@ -97,6 +99,8 @@ class ParseResource(SyncAPIResource):
 
           file_name: The name of the file to be parsed. If not set a name will be generated.
 
+          llm_processing: Controls the LLM used for the task.
+
           ocr_strategy: Controls the Optical Character Recognition (OCR) strategy.
 
               - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
@@ -146,6 +150,7 @@ class ParseResource(SyncAPIResource):
                     "error_handling": error_handling,
                     "expires_in": expires_in,
                     "file_name": file_name,
+                    "llm_processing": llm_processing,
                     "ocr_strategy": ocr_strategy,
                     "pipeline": pipeline,
                     "segment_processing": segment_processing,
@@ -251,6 +256,7 @@ class AsyncParseResource(AsyncAPIResource):
         error_handling: Literal["Fail", "Continue"] | Omit = omit,
         expires_in: Optional[int] | Omit = omit,
         file_name: Optional[str] | Omit = omit,
+        llm_processing: LlmProcessingParam | Omit = omit,
         ocr_strategy: Literal["All", "Auto"] | Omit = omit,
         pipeline: Literal["Azure", "Chunkr"] | Omit = omit,
         segment_processing: Optional[SegmentProcessingParam] | Omit = omit,
@@ -293,6 +299,8 @@ class AsyncParseResource(AsyncAPIResource):
 
           file_name: The name of the file to be parsed. If not set a name will be generated.
 
+          llm_processing: Controls the LLM used for the task.
+
           ocr_strategy: Controls the Optical Character Recognition (OCR) strategy.
 
               - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
@@ -342,6 +350,7 @@ class AsyncParseResource(AsyncAPIResource):
                     "error_handling": error_handling,
                     "expires_in": expires_in,
                     "file_name": file_name,
+                    "llm_processing": llm_processing,
                     "ocr_strategy": ocr_strategy,
                     "pipeline": pipeline,
                     "segment_processing": segment_processing,

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/__init__.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/file_info.py

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

chunkr_ai-0.1.0a11/src/chunkr_ai/types/llm_processing.py

@@ -0,0 +1,36 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union, Optional
+from typing_extensions import Literal, TypeAlias
+
+from pydantic import Field as FieldInfo
+
+from .._models import BaseModel
+
+__all__ = ["LlmProcessing", "FallbackStrategy", "FallbackStrategyModel"]
+
+
+class FallbackStrategyModel(BaseModel):
+    model: str = FieldInfo(alias="Model")
+    """Use a specific model as fallback"""
+
+
+FallbackStrategy: TypeAlias = Union[Literal["None", "Default"], FallbackStrategyModel]
+
+
+class LlmProcessing(BaseModel):
+    fallback_strategy: Optional[FallbackStrategy] = None
+    """The fallback strategy to use for the LLMs in the task."""
+
+    llm_model_id: Optional[str] = None
+    """The ID of the model to use for the task.
+
+    If not provided, the default model will be used. Please check the documentation
+    for the model you want to use.
+    """
+
+    max_completion_tokens: Optional[int] = None
+    """The maximum number of tokens to generate."""
+
+    temperature: Optional[float] = None
+    """The temperature to use for the LLM."""

chunkr_ai-0.1.0a11/src/chunkr_ai/types/llm_processing_param.py

@@ -0,0 +1,36 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union, Optional
+from typing_extensions import Literal, Required, Annotated, TypeAlias, TypedDict
+
+from .._utils import PropertyInfo
+
+__all__ = ["LlmProcessingParam", "FallbackStrategy", "FallbackStrategyModel"]
+
+
+class FallbackStrategyModel(TypedDict, total=False):
+    model: Required[Annotated[str, PropertyInfo(alias="Model")]]
+    """Use a specific model as fallback"""
+
+
+FallbackStrategy: TypeAlias = Union[Literal["None", "Default"], FallbackStrategyModel]
+
+
+class LlmProcessingParam(TypedDict, total=False):
+    fallback_strategy: FallbackStrategy
+    """The fallback strategy to use for the LLMs in the task."""
+
+    llm_model_id: Optional[str]
+    """The ID of the model to use for the task.
+
+    If not provided, the default model will be used. Please check the documentation
+    for the model you want to use.
+    """
+
+    max_completion_tokens: Optional[int]
+    """The maximum number of tokens to generate."""
+
+    temperature: float
+    """The temperature to use for the LLM."""

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/ocr_result.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/parse_configuration.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/parse_configuration_param.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/segment.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/segment_processing.py

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

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/segment_processing_param.py

@@ -48,24 +48,6 @@ class SegmentProcessingParam(TypedDict, total=False):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    form_region: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="FormRegion")]
-    """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.
 
@@ -84,60 +66,6 @@ class SegmentProcessingParam(TypedDict, total=False):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    graphical_item: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="GraphicalItem")]
-    """Controls the processing and generation for the segment.
-
-    - `crop_image` controls whether to crop the file's images to the segment's
-      bounding box. The cropped image will be stored in the segment's `image` field.
-      Use `All` to always crop, or `Auto` to only crop when needed for
-      post-processing.
-    - `format` specifies the output format: `Html` or `Markdown`
-    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
-      - `Auto`: Process content automatically
-      - `LLM`: Use large language models for processing
-      - `Ignore`: Exclude segments from final output
-    - `description` enables LLM-generated descriptions for segments. **Note:** This
-      uses chunkr's own VLM models and is not configurable via LLM processing
-      configuration.
-    - `extended_context` uses the full page image as context for LLM generation.
-    """
-
-    legend: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Legend")]
-    """Controls the processing and generation for the segment.
-
-    - `crop_image` controls whether to crop the file's images to the segment's
-      bounding box. The cropped image will be stored in the segment's `image` field.
-      Use `All` to always crop, or `Auto` to only crop when needed for
-      post-processing.
-    - `format` specifies the output format: `Html` or `Markdown`
-    - `strategy` determines how the content is generated: `Auto`, `LLM`, or `Ignore`
-      - `Auto`: Process content automatically
-      - `LLM`: Use large language models for processing
-      - `Ignore`: Exclude segments from final output
-    - `description` enables LLM-generated descriptions for segments. **Note:** This
-      uses chunkr's own VLM models and is not configurable via LLM processing
-      configuration.
-    - `extended_context` uses the full page image as context for LLM generation.
-    """
-
-    line_number: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="LineNumber")]
-    """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.
 
@@ -210,7 +138,7 @@ class SegmentProcessingParam(TypedDict, total=False):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    page_number: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="PageNumber")]
+    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
@@ -228,7 +156,7 @@ class SegmentProcessingParam(TypedDict, total=False):
     - `extended_context` uses the full page image as context for LLM generation.
     """
 
-    picture: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Picture")]
+    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
@@ -299,21 +227,3 @@ class SegmentProcessingParam(TypedDict, total=False):
       configuration.
     - `extended_context` uses the full page image as context for LLM generation.
     """
-
-    unknown: Annotated[Optional[GenerationConfigParam], PropertyInfo(alias="Unknown")]
-    """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-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/task_response.py

@@ -20,12 +20,6 @@ Output: TypeAlias = Union[ParseOutputResponse, ExtractOutputResponse, None]
 
 
 class TaskResponse(BaseModel):
-    completed: bool
-    """True when the task reaches a terminal state i.e.
-
-    `status` is `Succeeded` or `Failed` or `Cancelled`
-    """
-
     configuration: Configuration
     """
     Unified configuration type that can represent either parse or extract
@@ -64,8 +58,8 @@ class TaskResponse(BaseModel):
     output: Optional[Output] = None
     """Unified output type that can represent either parse or extract results"""
 
-    parse_task_id: Optional[str] = None
-    """The ID of the source `parse` task that was used for the task"""
+    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."""

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/tasks/extract_create_response.py

@@ -14,12 +14,6 @@ __all__ = ["ExtractCreateResponse"]
 
 
 class ExtractCreateResponse(BaseModel):
-    completed: bool
-    """True when the task reaches a terminal state i.e.
-
-    `status` is `Succeeded` or `Failed` or `Cancelled`
-    """
-
     configuration: ExtractConfiguration
 
     created_at: datetime
@@ -63,7 +57,7 @@ class ExtractCreateResponse(BaseModel):
       for that field.
     """
 
-    parse_task_id: Optional[str] = None
+    source_task_id: Optional[str] = None
     """The ID of the source `parse` task that was used for extraction"""
 
     started_at: Optional[datetime] = None

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/tasks/extract_get_response.py

@@ -14,12 +14,6 @@ __all__ = ["ExtractGetResponse"]
 
 
 class ExtractGetResponse(BaseModel):
-    completed: bool
-    """True when the task reaches a terminal state i.e.
-
-    `status` is `Succeeded` or `Failed` or `Cancelled`
-    """
-
     configuration: ExtractConfiguration
 
     created_at: datetime
@@ -63,7 +57,7 @@ class ExtractGetResponse(BaseModel):
       for that field.
     """
 
-    parse_task_id: Optional[str] = None
+    source_task_id: Optional[str] = None
     """The ID of the source `parse` task that was used for extraction"""
 
     started_at: Optional[datetime] = None

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/tasks/parse_create_params.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 from typing import Optional
 from typing_extensions import Literal, Required, TypedDict
 
+from ..llm_processing_param import LlmProcessingParam
 from ..chunk_processing_param import ChunkProcessingParam
 from ..segment_processing_param import SegmentProcessingParam
 
@@ -41,6 +42,9 @@ class ParseCreateParams(TypedDict, total=False):
     file_name: Optional[str]
     """The name of the file to be parsed. If not set a name will be generated."""
 
+    llm_processing: LlmProcessingParam
+    """Controls the LLM used for the task."""
+
     ocr_strategy: Literal["All", "Auto"]
     """Controls the Optical Character Recognition (OCR) strategy.
 

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/tasks/parse_create_response.py

@@ -14,12 +14,6 @@ __all__ = ["ParseCreateResponse"]
 
 
 class ParseCreateResponse(BaseModel):
-    completed: bool
-    """True when the task reaches a terminal state i.e.
-
-    `status` is `Succeeded` or `Failed` or `Cancelled`
-    """
-
     configuration: ParseConfiguration
 
     created_at: datetime

{chunkr_ai-0.1.0a10 → chunkr_ai-0.1.0a11}/src/chunkr_ai/types/tasks/parse_get_response.py

@@ -14,12 +14,6 @@ __all__ = ["ParseGetResponse"]
 
 
 class ParseGetResponse(BaseModel):
-    completed: bool
-    """True when the task reaches a terminal state i.e.
-
-    `status` is `Succeeded` or `Failed` or `Cancelled`
-    """
-
     configuration: ParseConfiguration
 
     created_at: datetime