Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

enhance: PR2998 add kwargs to ChunkrReaderConfig (#3247)

Wendong-Fan2a6944d68199
diff --git a/camel/loaders/chunkr_reader.py b/camel/loaders/chunkr_reader.py
index 279c97b4e..454de64fd 100644
--- a/camel/loaders/chunkr_reader.py
+++ b/camel/loaders/chunkr_reader.py
@@ -34,10 +34,12 @@ class ChunkrReaderConfig:
high_resolution (bool, optional): Whether to use high resolution OCR.
(default: :obj:`True`)
ocr_strategy (str, optional): The OCR strategy. Defaults to 'Auto'.
- **kwargs: Additional keyword arguments to pass to the Chunkr Configuration.
- This accepts all other Configuration parameters such as expires_in,
- pipeline, segment_processing, segmentation_strategy, etc.
- See: https://github.com/lumina-ai-inc/chunkr/blob/main/core/src/models/task.rs#L749
+ **kwargs: Additional keyword arguments to pass to the Chunkr
+ Configuration. This accepts all other Configuration parameters
+ such as expires_in, pipeline, segment_processing,
+ segmentation_strategy, etc.
+ See: https://github.com/lumina-ai-inc/chunkr/blob/main/core/src/
+ models/task.rs#L749
"""
def __init__(
@@ -181,7 +183,11 @@ class ChunkrReader:
Returns:
Configuration: Chunkr SDK configuration.
"""
- from chunkr_ai.models import ChunkProcessing, Configuration, OcrStrategy
+ from chunkr_ai.models import (
+ ChunkProcessing,
+ Configuration,
+ OcrStrategy,
+ )
return Configuration(
chunk_processing=ChunkProcessing(
diff --git a/test/loaders/test_chunkr_reader.py b/test/loaders/test_chunkr_reader.py
index fc5a646e5..1fe2758ee 100644
--- a/test/loaders/test_chunkr_reader.py
+++ b/test/loaders/test_chunkr_reader.py
@@ -21,14 +21,15 @@ from chunkr_ai.models import Status
from camel.loaders import ChunkrReader, ChunkrReaderConfig
-class TestChunkrReader(unittest.TestCase):
- def setUp(self):
- with patch('chunkr_ai.Chunkr'):
- self.reader = ChunkrReader(api_key="fake_api_key")
+class TestChunkrReader(unittest.IsolatedAsyncioTestCase):
+ @patch('chunkr_ai.Chunkr')
+ def setUp(self, mock_chunkr_class):
+ self.reader = ChunkrReader(api_key="fake_api_key")
+ self.mock_chunkr = self.reader._chunkr
@patch('chunkr_ai.Chunkr')
async def test_submit_task_success(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_task = AsyncMock()
mock_task.task_id = "12345"
mock_chunkr_instance.create_task = AsyncMock(return_value=mock_task)
@@ -40,7 +41,7 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_submit_task_with_config(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_task = AsyncMock()
mock_task.task_id = "12345"
mock_chunkr_instance.create_task = AsyncMock(return_value=mock_task)
@@ -55,7 +56,7 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_submit_task_failure(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_chunkr_instance.create_task = AsyncMock(side_effect=Exception())
with self.assertRaises(ValueError) as context:
@@ -66,10 +67,10 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_get_task_output_success(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_task = AsyncMock()
mock_task.status = Status.SUCCEEDED
- mock_task.json.return_value = {"status": "Succeeded"}
+ mock_task.json = MagicMock(return_value={"status": "Succeeded"})
mock_task.poll = AsyncMock()
mock_chunkr_instance.get_task = AsyncMock(return_value=mock_task)
@@ -82,7 +83,7 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_get_task_output_failed(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_task = AsyncMock()
mock_task.status = Status.FAILED
mock_task.poll = AsyncMock()
@@ -96,7 +97,7 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_get_task_output_get_task_error(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_chunkr_instance.get_task = AsyncMock(side_effect=Exception())
with self.assertRaises(ValueError) as context:
@@ -107,7 +108,7 @@ class TestChunkrReader(unittest.TestCase):
@patch('chunkr_ai.Chunkr')
async def test_get_task_output_poll_error(self, mock_chunkr_class):
- mock_chunkr_instance = mock_chunkr_class.return_value
+ mock_chunkr_instance = self.mock_chunkr
mock_task = AsyncMock()
mock_task.poll = AsyncMock(side_effect=Exception())
mock_chunkr_instance.get_task = AsyncMock(return_value=mock_task)
@@ -195,7 +196,7 @@ class TestChunkrReader(unittest.TestCase):
mock_chunk_processing.return_value = mock_chunk_processing_instance
mock_ocr_strategy.AUTO = "AUTO"
- result = self.reader._to_chunkr_configuration(config)
+ self.reader._to_chunkr_configuration(config)
mock_chunk_processing.assert_called_once_with(target_length=512)
mock_configuration.assert_called_once_with(
@@ -206,5 +207,6 @@ class TestChunkrReader(unittest.TestCase):
pipeline="test_pipeline",
)
+
if __name__ == "__main__":
unittest.main()