chunkr-ai 0.1.0a1__py3-none-any.whl → 0.1.0a3__py3-none-any.whl

chunkr_ai/types/task.py

@@ -1,31 +1,807 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-from typing import List, Optional
+from typing import List, Union, Optional
 from datetime import datetime
-from typing_extensions import Literal
+from typing_extensions import Literal, TypeAlias
+
+from pydantic import Field as FieldInfo
 
 from .._models import BaseModel
-from .bounding_box import BoundingBox
-from .llm_processing import LlmProcessing
-from .chunk_processing import ChunkProcessing
-from .segment_processing import SegmentProcessing
 
 __all__ = [
     "Task",
     "Configuration",
+    "ConfigurationChunkProcessing",
+    "ConfigurationChunkProcessingTokenizer",
+    "ConfigurationChunkProcessingTokenizerEnum",
+    "ConfigurationChunkProcessingTokenizerString",
+    "ConfigurationLlmProcessing",
+    "ConfigurationLlmProcessingFallbackStrategy",
+    "ConfigurationLlmProcessingFallbackStrategyModel",
+    "ConfigurationSegmentProcessing",
+    "ConfigurationSegmentProcessingCaption",
+    "ConfigurationSegmentProcessingFootnote",
+    "ConfigurationSegmentProcessingFormula",
+    "ConfigurationSegmentProcessingListItem",
+    "ConfigurationSegmentProcessingPage",
+    "ConfigurationSegmentProcessingPageFooter",
+    "ConfigurationSegmentProcessingPageHeader",
+    "ConfigurationSegmentProcessingPicture",
+    "ConfigurationSegmentProcessingSectionHeader",
+    "ConfigurationSegmentProcessingTable",
+    "ConfigurationSegmentProcessingText",
+    "ConfigurationSegmentProcessingTitle",
+    "ConfigurationClientVersion",
+    "ConfigurationClientVersionManualSDK",
+    "ConfigurationClientVersionGeneratedSDK",
     "Output",
     "OutputChunk",
     "OutputChunkSegment",
+    "OutputChunkSegmentBbox",
     "OutputChunkSegmentOcr",
+    "OutputChunkSegmentOcrBbox",
     "OutputChunkSegmentSSCell",
     "OutputChunkSegmentSSCellStyle",
+    "OutputChunkSegmentSSHeaderBbox",
     "OutputChunkSegmentSSHeaderOcr",
+    "OutputChunkSegmentSSHeaderOcrBbox",
     "OutputPage",
 ]
 
 
+class ConfigurationChunkProcessingTokenizerEnum(BaseModel):
+    enum: Literal["Word", "Cl100kBase", "XlmRobertaBase", "BertBaseUncased"] = FieldInfo(alias="Enum")
+    """Use one of the predefined tokenizer types"""
+
+
+class ConfigurationChunkProcessingTokenizerString(BaseModel):
+    string: str = FieldInfo(alias="String")
+    """
+    Use any Hugging Face tokenizer by specifying its model ID Examples:
+    "Qwen/Qwen-tokenizer", "facebook/bart-large"
+    """
+
+
+ConfigurationChunkProcessingTokenizer: TypeAlias = Union[
+    ConfigurationChunkProcessingTokenizerEnum, ConfigurationChunkProcessingTokenizerString
+]
+
+
+class ConfigurationChunkProcessing(BaseModel):
+    ignore_headers_and_footers: Optional[bool] = None
+    """DEPRECATED: use `segment_processing.ignore` instead"""
+
+    target_length: Optional[int] = None
+    """The target number of words in each chunk.
+
+    If 0, each chunk will contain a single segment.
+    """
+
+    tokenizer: Optional[ConfigurationChunkProcessingTokenizer] = None
+    """The tokenizer to use for the chunking process."""
+
+
+class ConfigurationLlmProcessingFallbackStrategyModel(BaseModel):
+    model: str = FieldInfo(alias="Model")
+    """Use a specific model as fallback"""
+
+
+ConfigurationLlmProcessingFallbackStrategy: TypeAlias = Union[
+    Literal["None", "Default"], ConfigurationLlmProcessingFallbackStrategyModel
+]
+
+
+class ConfigurationLlmProcessing(BaseModel):
+    fallback_strategy: Optional[ConfigurationLlmProcessingFallbackStrategy] = 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."""
+
+
+class ConfigurationSegmentProcessingCaption(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingFootnote(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingFormula(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingListItem(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingPage(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingPageFooter(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingPageHeader(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingPicture(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingSectionHeader(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingTable(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingText(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessingTitle(BaseModel):
+    crop_image: Optional[Literal["All", "Auto"]] = None
+    """Controls the cropping strategy for an item (e.g. segment, chunk, etc.)
+
+    - `All` crops all images in the item
+    - `Auto` crops images only if required for post-processing
+    """
+
+    description: Optional[bool] = None
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: Optional[List[Literal["Content", "HTML", "Markdown", "LLM"]]] = None
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: Optional[bool] = None
+    """Use the full page image as context for LLM generation"""
+
+    format: Optional[Literal["Html", "Markdown"]] = None
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str] = None
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Optional[Literal["LLM", "Auto", "Ignore"]] = None
+
+
+class ConfigurationSegmentProcessing(BaseModel):
+    caption: Optional[ConfigurationSegmentProcessingCaption] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    footnote: Optional[ConfigurationSegmentProcessingFootnote] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    formula: Optional[ConfigurationSegmentProcessingFormula] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    list_item: Optional[ConfigurationSegmentProcessingListItem] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    page: Optional[ConfigurationSegmentProcessingPage] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    page_footer: Optional[ConfigurationSegmentProcessingPageFooter] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    page_header: Optional[ConfigurationSegmentProcessingPageHeader] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    picture: Optional[ConfigurationSegmentProcessingPicture] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    section_header: Optional[ConfigurationSegmentProcessingSectionHeader] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    table: Optional[ConfigurationSegmentProcessingTable] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    text: Optional[ConfigurationSegmentProcessingText] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+    title: Optional[ConfigurationSegmentProcessingTitle] = 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.
+
+    **Deprecated fields (for backwards compatibility):**
+
+    - `llm` - **DEPRECATED**: Use `description` instead
+    - `embed_sources` - **DEPRECATED**: Embed field is auto-populated
+    - `html` - **DEPRECATED**: Use `format: Html` and `strategy` instead
+    - `markdown` - **DEPRECATED**: Use `format: Markdown` and `strategy` instead
+    """
+
+
+class ConfigurationClientVersionManualSDK(BaseModel):
+    manual_sdk: str = FieldInfo(alias="ManualSdk")
+    """Current manually-maintained SDK"""
+
+
+class ConfigurationClientVersionGeneratedSDK(BaseModel):
+    generated_sdk: str = FieldInfo(alias="GeneratedSdk")
+    """Future auto-generated SDK"""
+
+
+ConfigurationClientVersion: TypeAlias = Union[
+    Literal["Legacy"], ConfigurationClientVersionManualSDK, ConfigurationClientVersionGeneratedSDK, None
+]
+
+
 class Configuration(BaseModel):
-    chunk_processing: ChunkProcessing
+    chunk_processing: ConfigurationChunkProcessing
     """Controls the setting for the chunking and post-processing of each chunk."""
 
     error_handling: Literal["Fail", "Continue"]
@@ -36,7 +812,7 @@ class Configuration(BaseModel):
       LLM refusals etc.)
     """
 
-    llm_processing: LlmProcessing
+    llm_processing: ConfigurationLlmProcessing
     """Controls the LLM used for the task."""
 
     ocr_strategy: Literal["All", "Auto"]
@@ -48,7 +824,7 @@ class Configuration(BaseModel):
       used.
     """
 
-    segment_processing: SegmentProcessing
+    segment_processing: ConfigurationSegmentProcessing
     """Defines how each segment type is handled when generating the final output.
 
     Each segment uses one of three strategies. The chosen strategy controls: •
@@ -56,18 +832,14 @@ class Configuration(BaseModel):
     content is produced (rule-based vs. LLM). • The output format (`Html` or
     `Markdown`).
 
-    Optional flags such as image **cropping**, **extended context**, and **LLM
-    descriptions** further refine behaviour.
-
-    ---
+    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) • `Table` → **LLM** (HTML,
-    description on) • `Picture` → **LLM** (Markdown, description on, cropping _All_)
-    • `Formula`, `Page` → **LLM** (Markdown) • `PageHeader`, `PageFooter` →
-    **Ignore** (removed from output)
-
-    ---
+    `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.
@@ -83,6 +855,9 @@ class Configuration(BaseModel):
       layout element detection and only simple chunking.
     """
 
+    client_version: Optional[ConfigurationClientVersion] = None
+    """Client version for backwards compatibility processing"""
+
     expires_in: Optional[int] = None
     """
     The number of seconds until task is deleted. Expired tasks can **not** be
@@ -104,8 +879,36 @@ class Configuration(BaseModel):
     """
 
 
+class OutputChunkSegmentBbox(BaseModel):
+    height: float
+    """The height of the bounding box."""
+
+    left: float
+    """The left coordinate of the bounding box."""
+
+    top: float
+    """The top coordinate of the bounding box."""
+
+    width: float
+    """The width of the bounding box."""
+
+
+class OutputChunkSegmentOcrBbox(BaseModel):
+    height: float
+    """The height of the bounding box."""
+
+    left: float
+    """The left coordinate of the bounding box."""
+
+    top: float
+    """The top coordinate of the bounding box."""
+
+    width: float
+    """The width of the bounding box."""
+
+
 class OutputChunkSegmentOcr(BaseModel):
-    bbox: BoundingBox
+    bbox: OutputChunkSegmentOcrBbox
     """Bounding box for an item. It is used for chunks, segments and OCR results."""
 
     text: str
@@ -166,8 +969,36 @@ class OutputChunkSegmentSSCell(BaseModel):
     """
 
 
+class OutputChunkSegmentSSHeaderBbox(BaseModel):
+    height: float
+    """The height of the bounding box."""
+
+    left: float
+    """The left coordinate of the bounding box."""
+
+    top: float
+    """The top coordinate of the bounding box."""
+
+    width: float
+    """The width of the bounding box."""
+
+
+class OutputChunkSegmentSSHeaderOcrBbox(BaseModel):
+    height: float
+    """The height of the bounding box."""
+
+    left: float
+    """The left coordinate of the bounding box."""
+
+    top: float
+    """The top coordinate of the bounding box."""
+
+    width: float
+    """The width of the bounding box."""
+
+
 class OutputChunkSegmentSSHeaderOcr(BaseModel):
-    bbox: BoundingBox
+    bbox: OutputChunkSegmentSSHeaderOcrBbox
     """Bounding box for an item. It is used for chunks, segments and OCR results."""
 
     text: str
@@ -178,7 +1009,7 @@ class OutputChunkSegmentSSHeaderOcr(BaseModel):
 
 
 class OutputChunkSegment(BaseModel):
-    bbox: BoundingBox
+    bbox: OutputChunkSegmentBbox
     """Bounding box for an item. It is used for chunks, segments and OCR results."""
 
     page_height: float
@@ -248,7 +1079,7 @@ class OutputChunkSegment(BaseModel):
     ss_cells: Optional[List[OutputChunkSegmentSSCell]] = None
     """Cells of the segment. Only used for Spreadsheets."""
 
-    ss_header_bbox: Optional[BoundingBox] = None
+    ss_header_bbox: Optional[OutputChunkSegmentSSHeaderBbox] = None
     """Bounding box of the header of the segment, if found.
 
     Only used for Spreadsheets.
@@ -286,7 +1117,10 @@ class OutputChunkSegment(BaseModel):
 
 class OutputChunk(BaseModel):
     chunk_length: int
-    """The total number of tokens in the chunk. Calculated by the `tokenizer`."""
+    """The total number of tokens in the `embed` field of the chunk.
+
+    Calculated by the `tokenizer`.
+    """
 
     segments: List[OutputChunkSegment]
     """
@@ -299,12 +1133,17 @@ class OutputChunk(BaseModel):
     chunk_id: Optional[str] = None
     """The unique identifier for the chunk."""
 
+    content: Optional[str] = None
+    """The content of the chunk.
+
+    This is the text that is generated by combining the `content` field from each
+    segment. Can be used provided as context to the LLM.
+    """
+
     embed: Optional[str] = None
     """Suggested text to be embedded for the chunk.
 
-    This text is generated by combining the embed content from each segment
-    according to the configured embed sources (HTML, Markdown, LLM, or Content). Can
-    be configured using `embed_sources` in the `SegmentProcessing` configuration.
+    This text is generated by combining the `embed` field from each segment.
     """