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

chunkr_ai/types/task_parse_params.py

@@ -1,90 +0,0 @@
-# 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 Literal, Required, TypedDict
-
-from .llm_processing_param import LlmProcessingParam
-from .chunk_processing_param import ChunkProcessingParam
-from .segment_processing_param import SegmentProcessingParam
-
-__all__ = ["TaskParseParams"]
-
-
-class TaskParseParams(TypedDict, total=False):
-    file: Required[str]
-    """The file to be uploaded. Can be a URL or a base64 encoded file."""
-
-    chunk_processing: Optional[ChunkProcessingParam]
-    """Controls the setting for the chunking and post-processing of each chunk."""
-
-    error_handling: Optional[Literal["Fail", "Continue"]]
-    """Controls how errors are handled during processing:
-
-    - `Fail`: Stops processing and fails the task when any error occurs
-    - `Continue`: Attempts to continue processing despite non-critical errors (eg.
-      LLM refusals etc.)
-    """
-
-    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 uploaded. If not set a name will be generated."""
-
-    llm_processing: Optional[LlmProcessingParam]
-    """Controls the LLM used for the task."""
-
-    ocr_strategy: Optional[Literal["All", "Auto"]]
-    """Controls the Optical Character Recognition (OCR) strategy.
-
-    - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
-    - `Auto`: Selectively applies OCR only to pages with missing or low-quality
-      text. When text layer is present the bounding boxes from the text layer are
-      used.
-    """
-
-    pipeline: Optional[Literal["Azure", "Chunkr"]]
-    """
-    Choose the provider whose models will be used for segmentation and OCR. The
-    output will be unified to the Chunkr `output` format.
-    """
-
-    segment_processing: Optional[SegmentProcessingParam]
-    """Defines how each segment type is handled when generating the final output.
-
-    Each segment uses one of three strategies. The chosen strategy controls: •
-    Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`). • How the
-    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.
-
-    ---
-
-    **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)
-
-    ---
-
-    **Strategy reference** • **Auto** – rule-based content generation. • **LLM** –
-    generate content with an LLM. • **Ignore** – exclude the segment entirely.
-    """
-
-    segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]]
-    """Controls the segmentation strategy:
-
-    - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
-      `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-      segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
-    - `Page`: Treats each page as a single segment. Faster processing, but without
-      layout element detection and only simple chunking.
-    """

chunkr_ai/types/task_update_params.py

@@ -1,90 +0,0 @@
-# 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 Literal, TypedDict
-
-from .llm_processing_param import LlmProcessingParam
-from .chunk_processing_param import ChunkProcessingParam
-from .segment_processing_param import SegmentProcessingParam
-
-__all__ = ["TaskUpdateParams"]
-
-
-class TaskUpdateParams(TypedDict, total=False):
-    chunk_processing: Optional[ChunkProcessingParam]
-    """Controls the setting for the chunking and post-processing of each chunk."""
-
-    error_handling: Optional[Literal["Fail", "Continue"]]
-    """Controls how errors are handled during processing:
-
-    - `Fail`: Stops processing and fails the task when any error occurs
-    - `Continue`: Attempts to continue processing despite non-critical errors (eg.
-      LLM refusals etc.)
-    """
-
-    expires_in: Optional[int]
-    """
-    The number of seconds until task is deleted. Expired tasks can **not** be
-    updated, polled or accessed via web interface.
-    """
-
-    high_resolution: Optional[bool]
-    """Whether to use high-resolution images for cropping and post-processing.
-
-    (Latency penalty: ~7 seconds per page)
-    """
-
-    llm_processing: Optional[LlmProcessingParam]
-    """Controls the LLM used for the task."""
-
-    ocr_strategy: Optional[Literal["All", "Auto"]]
-    """Controls the Optical Character Recognition (OCR) strategy.
-
-    - `All`: Processes all pages with OCR. (Latency penalty: ~0.5 seconds per page)
-    - `Auto`: Selectively applies OCR only to pages with missing or low-quality
-      text. When text layer is present the bounding boxes from the text layer are
-      used.
-    """
-
-    pipeline: Optional[Literal["Azure", "Chunkr"]]
-    """
-    Choose the provider whose models will be used for segmentation and OCR. The
-    output will be unified to the Chunkr `output` format.
-    """
-
-    segment_processing: Optional[SegmentProcessingParam]
-    """Defines how each segment type is handled when generating the final output.
-
-    Each segment uses one of three strategies. The chosen strategy controls: •
-    Whether the segment is kept (`Auto`, `LLM`) or skipped (`Ignore`). • How the
-    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.
-
-    ---
-
-    **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)
-
-    ---
-
-    **Strategy reference** • **Auto** – rule-based content generation. • **LLM** –
-    generate content with an LLM. • **Ignore** – exclude the segment entirely.
-    """
-
-    segmentation_strategy: Optional[Literal["LayoutAnalysis", "Page"]]
-    """Controls the segmentation strategy:
-
-    - `LayoutAnalysis`: Analyzes pages for layout elements (e.g., `Table`,
-      `Picture`, `Formula`, etc.) using bounding boxes. Provides fine-grained
-      segmentation and better chunking. (Latency penalty: ~TBD seconds per page).
-    - `Page`: Treats each page as a single segment. Faster processing, but without
-      layout element detection and only simple chunking.
-    """

chunkr_ai-0.1.0a1.dist-info/RECORD

@@ -1,58 +0,0 @@
-chunkr_ai/__init__.py,sha256=scS30uHiCpLbaalKTAJSCFSTqnu_b9R5JCkTu2hmbzU,2587
-chunkr_ai/_base_client.py,sha256=Nv5b_rmVdmmPbF42mlOfymbSC6lxcYsrsvBhKSBDXWQ,67038
-chunkr_ai/_client.py,sha256=FHxLInwFr7bHnlt2oiZZCdGrYul-6uzkQk1byBxGTdE,15335
-chunkr_ai/_compat.py,sha256=VWemUKbj6DDkQ-O4baSpHVLJafotzeXmCQGJugfVTIw,6580
-chunkr_ai/_constants.py,sha256=S14PFzyN9-I31wiV7SmIlL5Ga0MLHxdvegInGdXH7tM,462
-chunkr_ai/_exceptions.py,sha256=ClgXUcwf4qhBTXnK4LzUPQCFdFldRxAlcYdOFFgpTxA,3220
-chunkr_ai/_files.py,sha256=KnEzGi_O756MvKyJ4fOCW_u3JhOeWPQ4RsmDvqihDQU,3545
-chunkr_ai/_models.py,sha256=KvjsMfb88XZlFUKVoOxr8OyDj47MhoH2OKqWNEbBhk4,30010
-chunkr_ai/_qs.py,sha256=AOkSz4rHtK4YI3ZU_kzea-zpwBUgEY8WniGmTPyEimc,4846
-chunkr_ai/_resource.py,sha256=f5tiwjxcKdbeMor8idoHtMFTUhqD9yc2xXtq5rqeLLk,1100
-chunkr_ai/_response.py,sha256=xXNpF53hiYARmAW7npKuxQ5UHAEjgAzm7ME_L3eIstY,28800
-chunkr_ai/_streaming.py,sha256=ZmyrVWk7-AWkLAATR55WgNxnyFzYmaqJt2LthA_PTqQ,10100
-chunkr_ai/_types.py,sha256=dnzU2Q2tLcuk29QFEcnPC1wp0-4XB4Cpef_3AnRhV5Y,6200
-chunkr_ai/_version.py,sha256=DjH8N3RuL6wzCqGACuOApaeMK7oF2_r00cZzxQ5fn4I,169
-chunkr_ai/pagination.py,sha256=mKx7wg1MEeJT-stWQ60VUHotL6Y3QdDmTr1fjG9scP4,1924
-chunkr_ai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chunkr_ai/_utils/__init__.py,sha256=PNZ_QJuzZEgyYXqkO1HVhGkj5IU9bglVUcw7H-Knjzw,2062
-chunkr_ai/_utils/_logs.py,sha256=ylZvP2JTPNlFCbxYajpsnWkA253kDFgnFYDWWuvgf_Q,780
-chunkr_ai/_utils/_proxy.py,sha256=aglnj2yBTDyGX9Akk2crZHrl10oqRmceUy2Zp008XEs,1975
-chunkr_ai/_utils/_reflection.py,sha256=ZmGkIgT_PuwedyNBrrKGbxoWtkpytJNU1uU4QHnmEMU,1364
-chunkr_ai/_utils/_resources_proxy.py,sha256=3KbSCApjaz7x_frFAxJe9ltY-dIJBQUVnIhR2GvVRY8,604
-chunkr_ai/_utils/_streams.py,sha256=SMC90diFFecpEg_zgDRVbdR3hSEIgVVij4taD-noMLM,289
-chunkr_ai/_utils/_sync.py,sha256=TpGLrrhRNWTJtODNE6Fup3_k7zrWm1j2RlirzBwre-0,2862
-chunkr_ai/_utils/_transform.py,sha256=n7kskEWz6o__aoNvhFoGVyDoalNe6mJwp-g7BWkdj88,15617
-chunkr_ai/_utils/_typing.py,sha256=D0DbbNu8GnYQTSICnTSHDGsYXj8TcAKyhejb0XcnjtY,4602
-chunkr_ai/_utils/_utils.py,sha256=ts4CiiuNpFiGB6YMdkQRh2SZvYvsl7mAF-JWHCcLDf4,12312
-chunkr_ai/lib/.keep,sha256=wuNrz-5SXo3jJaJOJgz4vFHM41YH_g20F5cRQo0vLes,224
-chunkr_ai/resources/__init__.py,sha256=zhuIEAnBOs0bLyNTeWngJbEFhlevoTx0NzTZMlX_cs8,976
-chunkr_ai/resources/health.py,sha256=XTvUtRs5hEK-uccb_40mcIex85eEUo1a171nQUjpSOs,4965
-chunkr_ai/resources/task.py,sha256=Is4Z8lhKfxAiITBmSv7E6oebCiZEoNBA4xiHl-L1yEU,48182
-chunkr_ai/types/__init__.py,sha256=_SppK-MG3ZexF2C3d89XcrQWcnShexkVYAIBcHA5Qb0,1901
-chunkr_ai/types/auto_generation_config.py,sha256=6j9Kbj05FObYmp2g8oPOY69AxlPr6-TLC9p91Qx_SDo,1337
-chunkr_ai/types/auto_generation_config_param.py,sha256=SIp5SSE060DiKQW0QOHXgqYbKZisPqn6koeowehvJCI,1251
-chunkr_ai/types/bounding_box.py,sha256=JDZlhJJl4lg6RYGf8VpC46soQfQ10-K8YwHHA6XBFkM,431
-chunkr_ai/types/chunk_processing.py,sha256=KWnebuSLIwSWPaHSmAGUPZAMrkbDKA6RYDq9TwrQZJk,1217
-chunkr_ai/types/chunk_processing_param.py,sha256=7Yq6ZpuMNnyqc08GLow4lsGA_vpI7S5tWMac5T4Hyak,1294
-chunkr_ai/types/health_check_response.py,sha256=6Zn5YYHCQf2RgMjDlf39mtiTPqfaBfC9Vv599U_rKCI,200
-chunkr_ai/types/ignore_generation_config.py,sha256=lU2qjsombMTlsQHGtvs2G-FaNBL1mHmF8BThYMd1UYk,1341
-chunkr_ai/types/ignore_generation_config_param.py,sha256=-gdBQy4HffH7GQwEXMvSfeHC5fgiMry3jHVEwrLUPrM,1255
-chunkr_ai/types/llm_generation_config.py,sha256=ifPhOvYrC968WfaI3z0qwQyUewyWdtEDUnuWEhNJN7o,1335
-chunkr_ai/types/llm_generation_config_param.py,sha256=s3iWDYtQ04FWubWWl22cIFTNiwhLzluAyt6zmNcNCd4,1249
-chunkr_ai/types/llm_processing.py,sha256=f6w52vkvQKHu1HxWD0r9xZ9BlufMcRiY47hBVpeFPTw,1132
-chunkr_ai/types/llm_processing_param.py,sha256=GlvSYRc-_1ec1TgZiybY7G5unzdDpIJiKcs7Ou4cbPo,1131
-chunkr_ai/types/picture_generation_config.py,sha256=-W4SkGwuK6DmMoA_CbgHz-dfYKq2bF1vlZUcWiTFKsc,1343
-chunkr_ai/types/picture_generation_config_param.py,sha256=G5czQb5jbuYajBPojYah8_QFl7Hw0gXNojxtwixy8Ao,1257
-chunkr_ai/types/segment_processing.py,sha256=3K50PMRUeTLZ7rUzLXsQyqFga0lYjGAer7xotHFFZn8,14132
-chunkr_ai/types/segment_processing_param.py,sha256=AV9PRcdXRVcrjMXNNhTxnJflCFsib_shmb0MSYHgrjs,14306
-chunkr_ai/types/table_generation_config.py,sha256=TQqAKji9Bf7N8UBN9nM0cyEp3g3e7tbN-Ehjr2uHTVE,1339
-chunkr_ai/types/table_generation_config_param.py,sha256=KLgSwuA2bB_ASg8vIhsBJTkMDPqBZJQcwl75u7NaQm8,1253
-chunkr_ai/types/task.py,sha256=CqrrvA_wPGALVxLQXN4m6cXAavXh1DoLnLljPVQjef4,11992
-chunkr_ai/types/task_get_params.py,sha256=Nx2luhebcoaiuRln4KP4FarWvBPd1OYi__efi56zHPM,460
-chunkr_ai/types/task_list_params.py,sha256=fCku42QW6QUsLmZgKJBaxisGvUcmcQ5fa6LgHHRIwiQ,1043
-chunkr_ai/types/task_parse_params.py,sha256=3IpiYdCi54DlROXaB_vx-hIZ5pk3tkSBRiftAcwq8h8,3585
-chunkr_ai/types/task_update_params.py,sha256=Vfgoshoig9MWtkBv0VeDFfBmtgktap6-Mm9R1SwHw68,3532
-chunkr_ai-0.1.0a1.dist-info/METADATA,sha256=_KVY6caTB5upWNyQfhJYScFOlkBySVutRplRq_JGn4A,15782
-chunkr_ai-0.1.0a1.dist-info/WHEEL,sha256=C2FUgwZgiLbznR-k0b_5k3Ai_1aASOXDss3lzCUsUug,87
-chunkr_ai-0.1.0a1.dist-info/licenses/LICENSE,sha256=3FDRL-L-DFkrFy8yJpb1Nxhuztm0PB2kawcCgK5utFg,11336
-chunkr_ai-0.1.0a1.dist-info/RECORD,,