chunkr-ai 0.1.0__py3-none-any.whl → 0.1.0a1__py3-none-any.whl

chunkr_ai/types/__init__.py

@@ -0,0 +1,27 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .task import Task as Task
+from .bounding_box import BoundingBox as BoundingBox
+from .llm_processing import LlmProcessing as LlmProcessing
+from .task_get_params import TaskGetParams as TaskGetParams
+from .chunk_processing import ChunkProcessing as ChunkProcessing
+from .task_list_params import TaskListParams as TaskListParams
+from .task_parse_params import TaskParseParams as TaskParseParams
+from .segment_processing import SegmentProcessing as SegmentProcessing
+from .task_update_params import TaskUpdateParams as TaskUpdateParams
+from .llm_processing_param import LlmProcessingParam as LlmProcessingParam
+from .health_check_response import HealthCheckResponse as HealthCheckResponse
+from .llm_generation_config import LlmGenerationConfig as LlmGenerationConfig
+from .auto_generation_config import AutoGenerationConfig as AutoGenerationConfig
+from .chunk_processing_param import ChunkProcessingParam as ChunkProcessingParam
+from .table_generation_config import TableGenerationConfig as TableGenerationConfig
+from .ignore_generation_config import IgnoreGenerationConfig as IgnoreGenerationConfig
+from .segment_processing_param import SegmentProcessingParam as SegmentProcessingParam
+from .picture_generation_config import PictureGenerationConfig as PictureGenerationConfig
+from .llm_generation_config_param import LlmGenerationConfigParam as LlmGenerationConfigParam
+from .auto_generation_config_param import AutoGenerationConfigParam as AutoGenerationConfigParam
+from .table_generation_config_param import TableGenerationConfigParam as TableGenerationConfigParam
+from .ignore_generation_config_param import IgnoreGenerationConfigParam as IgnoreGenerationConfigParam
+from .picture_generation_config_param import PictureGenerationConfigParam as PictureGenerationConfigParam

chunkr_ai/types/auto_generation_config.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["AutoGenerationConfig"]
+
+
+class AutoGenerationConfig(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

chunkr_ai/types/auto_generation_config_param.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["AutoGenerationConfigParam"]
+
+
+class AutoGenerationConfigParam(TypedDict, total=False):
+    crop_image: Literal["All", "Auto"]
+    """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: bool
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: List[Literal["Content", "HTML", "Markdown", "LLM"]]
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: bool
+    """Use the full page image as context for LLM generation"""
+
+    format: Literal["Html", "Markdown"]
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str]
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Literal["LLM", "Auto", "Ignore"]

chunkr_ai/types/bounding_box.py

@@ -0,0 +1,19 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .._models import BaseModel
+
+__all__ = ["BoundingBox"]
+
+
+class BoundingBox(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."""

chunkr_ai/types/chunk_processing.py

@@ -0,0 +1,40 @@
+# 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__ = ["ChunkProcessing", "Tokenizer", "TokenizerEnum", "TokenizerString"]
+
+
+class TokenizerEnum(BaseModel):
+    enum: Literal["Word", "Cl100kBase", "XlmRobertaBase", "BertBaseUncased"] = FieldInfo(alias="Enum")
+    """Use one of the predefined tokenizer types"""
+
+
+class TokenizerString(BaseModel):
+    string: str = FieldInfo(alias="String")
+    """
+    Use any Hugging Face tokenizer by specifying its model ID Examples:
+    "Qwen/Qwen-tokenizer", "facebook/bart-large"
+    """
+
+
+Tokenizer: TypeAlias = Union[TokenizerEnum, TokenizerString]
+
+
+class ChunkProcessing(BaseModel):
+    ignore_headers_and_footers: Optional[bool] = None
+    """DEPRECATED: use `segment_processing.ignore` This value will not be used"""
+
+    target_length: Optional[int] = None
+    """The target number of words in each chunk.
+
+    If 0, each chunk will contain a single segment.
+    """
+
+    tokenizer: Optional[Tokenizer] = None
+    """The tokenizer to use for the chunking process."""

chunkr_ai/types/chunk_processing_param.py

@@ -0,0 +1,42 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union
+from typing_extensions import Literal, Required, Annotated, TypeAlias, TypedDict
+
+from .._utils import PropertyInfo
+
+__all__ = ["ChunkProcessingParam", "Tokenizer", "TokenizerEnum", "TokenizerString"]
+
+
+class TokenizerEnum(TypedDict, total=False):
+    enum: Required[
+        Annotated[Literal["Word", "Cl100kBase", "XlmRobertaBase", "BertBaseUncased"], PropertyInfo(alias="Enum")]
+    ]
+    """Use one of the predefined tokenizer types"""
+
+
+class TokenizerString(TypedDict, total=False):
+    string: Required[Annotated[str, PropertyInfo(alias="String")]]
+    """
+    Use any Hugging Face tokenizer by specifying its model ID Examples:
+    "Qwen/Qwen-tokenizer", "facebook/bart-large"
+    """
+
+
+Tokenizer: TypeAlias = Union[TokenizerEnum, TokenizerString]
+
+
+class ChunkProcessingParam(TypedDict, total=False):
+    ignore_headers_and_footers: bool
+    """DEPRECATED: use `segment_processing.ignore` This value will not be used"""
+
+    target_length: int
+    """The target number of words in each chunk.
+
+    If 0, each chunk will contain a single segment.
+    """
+
+    tokenizer: Tokenizer
+    """The tokenizer to use for the chunking process."""

chunkr_ai/types/health_check_response.py

@@ -0,0 +1,7 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing_extensions import TypeAlias
+
+__all__ = ["HealthCheckResponse"]
+
+HealthCheckResponse: TypeAlias = str

chunkr_ai/types/ignore_generation_config.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["IgnoreGenerationConfig"]
+
+
+class IgnoreGenerationConfig(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

chunkr_ai/types/ignore_generation_config_param.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["IgnoreGenerationConfigParam"]
+
+
+class IgnoreGenerationConfigParam(TypedDict, total=False):
+    crop_image: Literal["All", "Auto"]
+    """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: bool
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: List[Literal["Content", "HTML", "Markdown", "LLM"]]
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: bool
+    """Use the full page image as context for LLM generation"""
+
+    format: Literal["Html", "Markdown"]
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str]
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Literal["LLM", "Auto", "Ignore"]

chunkr_ai/types/llm_generation_config.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["LlmGenerationConfig"]
+
+
+class LlmGenerationConfig(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

chunkr_ai/types/llm_generation_config_param.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["LlmGenerationConfigParam"]
+
+
+class LlmGenerationConfigParam(TypedDict, total=False):
+    crop_image: Literal["All", "Auto"]
+    """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: bool
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: List[Literal["Content", "HTML", "Markdown", "LLM"]]
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: bool
+    """Use the full page image as context for LLM generation"""
+
+    format: Literal["Html", "Markdown"]
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str]
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Literal["LLM", "Auto", "Ignore"]

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."""
+
+    max_completion_tokens: Optional[int] = None
+    """The maximum number of tokens to generate."""
+
+    api_model_id: Optional[str] = FieldInfo(alias="model_id", default=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.
+    """
+
+    temperature: Optional[float] = None
+    """The temperature to use for the LLM."""

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."""
+
+    max_completion_tokens: Optional[int]
+    """The maximum number of tokens to generate."""
+
+    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.
+    """
+
+    temperature: float
+    """The temperature to use for the LLM."""

chunkr_ai/types/picture_generation_config.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from .._models import BaseModel
+
+__all__ = ["PictureGenerationConfig"]
+
+
+class PictureGenerationConfig(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

chunkr_ai/types/picture_generation_config_param.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import List, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["PictureGenerationConfigParam"]
+
+
+class PictureGenerationConfigParam(TypedDict, total=False):
+    crop_image: Literal["All", "Auto"]
+    """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: bool
+    """Generate LLM descriptions for this segment"""
+
+    embed_sources: List[Literal["Content", "HTML", "Markdown", "LLM"]]
+    """**DEPRECATED**: `embed` field is auto populated"""
+
+    extended_context: bool
+    """Use the full page image as context for LLM generation"""
+
+    format: Literal["Html", "Markdown"]
+
+    html: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: html` and `strategy` instead."""
+
+    llm: Optional[str]
+    """**DEPRECATED**: use description instead"""
+
+    markdown: Optional[Literal["LLM", "Auto", "Ignore"]]
+    """**DEPRECATED**: Use `format: markdown` and `strategy` instead."""
+
+    strategy: Literal["LLM", "Auto", "Ignore"]