chunkr-ai 0.0.48__tar.gz → 0.0.49__tar.gz

{chunkr_ai-0.0.48/src/chunkr_ai.egg-info → chunkr_ai-0.0.49}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chunkr-ai
-Version: 0.0.48
+Version: 0.0.49
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 License: MIT License

{chunkr_ai-0.0.48 → chunkr_ai-0.0.49}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "chunkr-ai"
-version = "0.0.48"
+version = "0.0.49"
 authors = [{"name" = "Ishaan Kapoor", "email" = "ishaan@lumina.sh"}]
 description = "Python client for Chunkr: open source document intelligence"
 readme = "README.md"

{chunkr_ai-0.0.48 → chunkr_ai-0.0.49}/src/chunkr_ai/api/configuration.py

@@ -23,6 +23,7 @@ class GenerationConfig(BaseModel):
     markdown: Optional[GenerationStrategy] = None
     crop_image: Optional[CroppingStrategy] = None
     embed_sources: Optional[List[EmbedSource]] = Field(default_factory=lambda: [EmbedSource.MARKDOWN])
+    extended_context: Optional[bool] = None
 
 class SegmentProcessing(BaseModel):
     model_config = ConfigDict(populate_by_name=True, alias_generator=str.title)

{chunkr_ai-0.0.48 → chunkr_ai-0.0.49/src/chunkr_ai.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chunkr-ai
-Version: 0.0.48
+Version: 0.0.49
 Summary: Python client for Chunkr: open source document intelligence
 Author-email: Ishaan Kapoor <ishaan@lumina.sh>
 License: MIT License

{chunkr_ai-0.0.48 → chunkr_ai-0.0.49}/tests/test_chunkr.py

@@ -2,27 +2,25 @@ import pytest
 from pathlib import Path
 from PIL import Image
 import asyncio
-import base64
-import io
-import tempfile
 from typing import Awaitable
 
 from chunkr_ai import Chunkr
 from chunkr_ai.models import (
+    ChunkProcessing,
     Configuration,
-    GenerationStrategy,
+    EmbedSource,
+    ErrorHandlingStrategy,
+    FallbackStrategy,
     GenerationConfig,
+    GenerationStrategy,
+    LlmProcessing,
     OcrStrategy,
     Pipeline,
     SegmentationStrategy,
     SegmentProcessing,
-    ChunkProcessing,
+    Status,
     TaskResponse,
-    EmbedSource,
-    ErrorHandlingStrategy,
     Tokenizer,
-    LlmProcessing,
-    FallbackStrategy,
 )
 
 @pytest.fixture
@@ -167,6 +165,21 @@ def model_fallback_config():
         ),
     )
 
+@pytest.fixture
+def extended_context_config():
+    return Configuration(
+        segment_processing=SegmentProcessing(
+            picture=GenerationConfig(
+                extended_context=True,
+                html=GenerationStrategy.LLM,
+            ),
+            table=GenerationConfig(
+                extended_context=True,
+                html=GenerationStrategy.LLM,
+            )
+        ),
+    )
+
 @pytest.mark.asyncio
 async def test_ocr_auto(client, sample_path):
     response = await client.upload(sample_path, Configuration(ocr_strategy=OcrStrategy.AUTO))
@@ -265,9 +278,18 @@ async def test_cancel_task(client, sample_path):
 @pytest.mark.asyncio
 async def test_cancel_task_direct(client, sample_path):
     task = await client.create_task(sample_path)
-    assert isinstance(task, Awaitable) and isinstance(task, TaskResponse)
     assert task.status == "Starting"
-    await task.cancel()
+    try:
+        await task.cancel()
+    except Exception as e:
+        task = await client.get_task(task.task_id)
+        print(task.status)
+        if task.status == Status.PROCESSING:
+            print("Task is processing, so it can't be cancelled")
+            assert True
+        else:
+            print("Task status:", task.status)
+            raise e
     assert task.status == "Cancelled"
 
 @pytest.mark.asyncio
@@ -304,6 +326,7 @@ async def test_pipeline_type_azure(client, sample_path):
     assert response.task_id is not None
     assert response.status == "Succeeded"
     assert response.output is not None
+    assert response.configuration.pipeline == Pipeline.AZURE
     
 @pytest.mark.asyncio
 async def test_pipeline_type_chunkr(client, sample_path):
@@ -311,7 +334,8 @@ async def test_pipeline_type_chunkr(client, sample_path):
     assert response.task_id is not None
     assert response.status == "Succeeded"
     assert response.output is not None
-
+    assert response.configuration.pipeline == Pipeline.CHUNKR
+    
 @pytest.mark.asyncio
 async def test_client_lifecycle(client, sample_path):
     response1 = await client.upload(sample_path)
@@ -528,4 +552,33 @@ async def test_fallback_strategy_serialization():
     # Test string representation
     assert str(none_strategy) == "None"
     assert str(default_strategy) == "Default"
-    assert str(model_strategy) == "Model(gpt-4.1)"
+    assert str(model_strategy) == "Model(gpt-4.1)"
+
+@pytest.mark.asyncio
+async def test_extended_context(client, sample_path, extended_context_config):
+    """Tests uploading with extended context enabled for pictures and tables."""
+    print("\nTesting extended context for Pictures and Tables...")
+    try:
+        task = await client.upload(sample_path, config=extended_context_config)
+        print(f"Task created with extended context config: {task.task_id}")
+        print(f"Initial Status: {task.status}")
+
+        # Poll the task until it finishes or fails
+        print(f"Final Status: {task.status}")
+        print(f"Message: {task.message}")
+
+        # Basic assertion: Check if the task completed (either succeeded or failed)
+        assert task.status in [Status.SUCCEEDED, Status.FAILED], f"Task ended in unexpected state: {task.status}"
+
+        # More specific assertions based on expected outcomes with your local server
+        # if task.status == Status.FAILED:
+        #     assert "context_length_exceeded" in task.message, "Expected context length error"
+        # elif task.status == Status.SUCCEEDED:
+        #     # Check if output reflects extended context usage if possible
+        #     pass
+
+        print("Extended context test completed.")
+
+    except Exception as e:
+        print(f"Error during extended context test: {e}")
+        raise # Re-raise the exception to fail the test explicitly