[Improvement] Add support for min chunk size (#1007)

This commit is contained in:
Deven Patel
2023-12-15 05:59:15 +05:30
committed by GitHub
parent 9303a1bf81
commit c0ee680546
11 changed files with 59 additions and 25 deletions

View File

@@ -11,7 +11,7 @@ class TestImageChunker(unittest.TestCase):
Test the chunks generated by TextChunker.
# TODO: Not a very precise test.
"""
chunker_config = ChunkerConfig(chunk_size=1, chunk_overlap=0, length_function=len)
chunker_config = ChunkerConfig(chunk_size=1, chunk_overlap=0, length_function=len, min_chunk_size=0)
chunker = ImagesChunker(config=chunker_config)
# Data type must be set manually in the test
chunker.set_data_type(DataType.IMAGES)
@@ -51,7 +51,7 @@ class TestImageChunker(unittest.TestCase):
self.assertEqual(expected_chunks, result)
def test_word_count(self):
chunker_config = ChunkerConfig(chunk_size=1, chunk_overlap=0, length_function=len)
chunker_config = ChunkerConfig(chunk_size=1, chunk_overlap=0, length_function=len, min_chunk_size=0)
chunker = ImagesChunker(config=chunker_config)
chunker.set_data_type(DataType.IMAGES)