chunkr-ai 0.0.44__tar.gz → 0.0.45__tar.gz

{chunkr_ai-0.0.44/src/chunkr_ai.egg-info → chunkr_ai-0.0.45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chunkr-ai
-Version: 0.0.44
+Version: 0.0.45
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 License: MIT License

{chunkr_ai-0.0.44 → chunkr_ai-0.0.45}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "chunkr-ai"
-version = "0.0.44"
+version = "0.0.45"
 authors = [{"name" = "Ishaan Kapoor", "email" = "ishaan@lumina.sh"}]
 description = "Python client for Chunkr: open source document intelligence"
 readme = "README.md"

{chunkr_ai-0.0.44 → chunkr_ai-0.0.45}/src/chunkr_ai/api/configuration.py

@@ -126,6 +126,10 @@ class SegmentationStrategy(str, Enum):
     LAYOUT_ANALYSIS = "LayoutAnalysis"
     PAGE = "Page"
 
+class ErrorHandlingStrategy(str, Enum):
+    FAIL = "Fail"
+    CONTINUE = "Continue"
+
 class BoundingBox(BaseModel):
     left: float
     top: float
@@ -189,6 +193,7 @@ class Pipeline(str, Enum):
 class Configuration(BaseModel):
     chunk_processing: Optional[ChunkProcessing] = None
     expires_in: Optional[int] = None
+    error_handling: Optional[ErrorHandlingStrategy] = None
     high_resolution: Optional[bool] = None
     ocr_strategy: Optional[OcrStrategy] = None
     segment_processing: Optional[SegmentProcessing] = None

{chunkr_ai-0.0.44 → chunkr_ai-0.0.45}/src/chunkr_ai/models.py

@@ -5,6 +5,7 @@ from .api.configuration import (
     Configuration,
     CroppingStrategy,
     EmbedSource,
+    ErrorHandlingStrategy,
     GenerationStrategy,
     GenerationConfig,
     Model,
@@ -29,6 +30,7 @@ __all__ = [
     "Configuration",
     "CroppingStrategy",
     "EmbedSource",
+    "ErrorHandlingStrategy",
     "GenerationConfig",
     "GenerationStrategy",
     "Model",

{chunkr_ai-0.0.44 → chunkr_ai-0.0.45/src/chunkr_ai.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chunkr-ai
-Version: 0.0.44
+Version: 0.0.45
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 License: MIT License

{chunkr_ai-0.0.44 → chunkr_ai-0.0.45}/tests/test_chunkr.py

@@ -16,6 +16,7 @@ from chunkr_ai.models import (
     ChunkProcessing,
     TaskResponse,
     EmbedSource,
+    ErrorHandlingStrategy,
     Tokenizer,
 )
 
@@ -442,4 +443,11 @@ async def test_embed_sources_with_different_tokenizer(client, sample_path, xlm_r
     response = await client.upload(sample_path, xlm_roberta_with_html_content_config)
     assert response.task_id is not None
     assert response.status == "Succeeded"
-    assert response.output is not None
+    assert response.output is not None
+
+@pytest.mark.asyncio
+async def test_error_handling_continue(client, sample_path):
+    response = await client.upload(sample_path, Configuration(error_handling=ErrorHandlingStrategy.CONTINUE))
+    assert response.task_id is not None
+    assert response.status == "Succeeded"
+    assert response.output is not None