chunkr-ai 0.0.15__tar.gz → 0.0.16__tar.gz

{chunkr_ai-0.0.15/src/chunkr_ai.egg-info → chunkr_ai-0.0.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: chunkr-ai
-Version: 0.0.15
+Version: 0.0.16
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 Project-URL: Homepage, https://chunkr.ai

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "chunkr-ai"
-version = "0.0.15"
+version = "0.0.16"
 authors = [{"name" = "Ishaan Kapoor", "email" = "ishaan@lumina.sh"}]
 description = "Python client for Chunkr: open source document intelligence"
 readme = "README.md"

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/src/chunkr_ai/api/config.py

@@ -127,6 +127,8 @@ class Model(str, Enum):
     FAST = "Fast"
     HIGH_QUALITY = "HighQuality"
 
+class PipelineType(str, Enum):
+    AZURE = "Azure"
 
 class Configuration(BaseModel):
     chunk_processing: Optional[ChunkProcessing] = Field(default=None)
@@ -139,6 +141,7 @@ class Configuration(BaseModel):
     ocr_strategy: Optional[OcrStrategy] = Field(default=None)
     segment_processing: Optional[SegmentProcessing] = Field(default=None)
     segmentation_strategy: Optional[SegmentationStrategy] = Field(default=None)
+    pipeline: Optional[PipelineType] = Field(default=None)
 
     @model_validator(mode="before")
     def map_deprecated_fields(cls, values: Dict) -> Dict:

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/src/chunkr_ai/api/misc.py

@@ -3,6 +3,7 @@ import io
 import json
 from pathlib import Path
 from PIL import Image
+from pydantic import BaseModel
 import requests
 from typing import Union, Tuple, BinaryIO, Optional
 

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/src/chunkr_ai/api/task_base.py

@@ -7,7 +7,6 @@ from datetime import datetime
 
 T = TypeVar("T", bound="TaskBase")
 
-
 class TaskBase(BaseModel, ABC, Generic[T]):
     configuration: Configuration
     created_at: datetime
@@ -63,12 +62,15 @@ class TaskBase(BaseModel, ABC, Generic[T]):
         return None
 
     def html(self) -> str:
+        """Get the full HTML of the task"""
         return self._get_content("html")
 
     def markdown(self) -> str:
+        """Get the full markdown of the task"""
         return self._get_content("markdown")
 
     def content(self) -> str:
+        """Get the full content of the task"""
         return self._get_content("content")
 
     def _get_content(self, t: str) -> str:

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/src/chunkr_ai/models.py

@@ -18,6 +18,7 @@ from .api.config import (
     SegmentType,
     SegmentationStrategy,
     Status,
+    PipelineType,
 )
 
 from .api.task import TaskResponse
@@ -45,4 +46,5 @@ __all__ = [
     "Status",
     "TaskResponse",
     "TaskResponseAsync",
+    "PipelineType",
 ]

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16/src/chunkr_ai.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: chunkr-ai
-Version: 0.0.15
+Version: 0.0.16
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 Project-URL: Homepage, https://chunkr.ai

{chunkr_ai-0.0.15 → chunkr_ai-0.0.16}/tests/test_chunkr.py

@@ -10,6 +10,7 @@ from chunkr_ai.models import (
     GenerationConfig,
     JsonSchema,
     OcrStrategy,
+    PipelineType,
     Property,
     SegmentationStrategy,
     SegmentProcessing,
@@ -38,6 +39,14 @@ def sample_image():
     return img
 
 
+@pytest.fixture(params=[
+    pytest.param(None, id="none_pipeline"),
+    pytest.param(PipelineType.AZURE, id="azure_pipeline"),
+])
+def pipeline_type(request):
+    return request.param
+
+
 @pytest.mark.asyncio
 async def test_send_file_path(chunkr_client, sample_path):
     client_type, client = chunkr_client
@@ -411,3 +420,17 @@ async def test_update_task_direct(chunkr_client, sample_path):
     assert task.status == "Succeeded"
     assert task.output is not None
     assert task.configuration.segmentation_strategy == SegmentationStrategy.PAGE
+
+
+@pytest.mark.asyncio
+async def test_pipeline_type(chunkr_client, sample_path, pipeline_type):
+    client_type, client = chunkr_client
+    response = (
+        await client.upload(sample_path, Configuration(pipeline=pipeline_type))
+        if client_type == "async"
+        else client.upload(sample_path, Configuration(pipeline=pipeline_type))
+    )
+
+    assert response.task_id is not None
+    assert response.status == "Succeeded"
+    assert response.output is not None