Add support for image dataset (#571)

Co-authored-by: Rupesh Bansal <rupeshbansal@Shankars-MacBook-Air.local>
This commit is contained in:
Rupesh Bansal
2023-10-04 09:50:40 +05:30
committed by GitHub
parent 55e9a1cbd6
commit d0af018b8d
19 changed files with 498 additions and 31 deletions

View File

@@ -62,6 +62,15 @@ class TestTextChunker(unittest.TestCase):
self.assertEqual(len(documents), len(text))
def test_word_count(self):
chunker_config = ChunkerConfig(chunk_size=1, chunk_overlap=0, length_function=len)
chunker = TextChunker(config=chunker_config)
chunker.set_data_type(DataType.TEXT)
document = ["ab cd", "ef gh"]
result = chunker.get_word_count(document)
self.assertEqual(result, 4)
class MockLoader:
def load_data(self, src):