Fix PdfDocument teset, give chunk_by_sentence a maximum_length arg

cognee/tasks/chunks/chunk_by_sentence.py

@@ -5,7 +5,7 @@ from uuid import uuid4
 from typing import Optional
 from .chunk_by_word import chunk_by_word
 
-def chunk_by_sentence(data: str, maximum_length: Optional[int]):
+def chunk_by_sentence(data: str, maximum_length: Optional[int] = None):
     sentence = ""
     paragraph_id = uuid4()
     chunk_index = 0

cognee/tests/unit/documents/PdfDocument_test.py

@@ -4,8 +4,8 @@ import uuid
 from cognee.modules.data.processing.document_types.PdfDocument import PdfDocument
 
 GROUND_TRUTH = [
-    {"word_count": 879, "len_text": 5622, "cut_type": "sentence_end"},
-    {"word_count": 951, "len_text": 6384, "cut_type": "sentence_end"},
+    {"word_count": 879, "len_text": 5607, "cut_type": "sentence_end"},
+    {"word_count": 953, "len_text": 6363, "cut_type": "sentence_end"},
 ]
 
 

cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py

@@ -49,7 +49,7 @@ Third paragraph is cut and is missing the dot at the end""",
 
 def run_chunking_test(test_text, expected_chunks):
     chunks = []
-    for chunk_data in chunk_by_paragraph(test_text, 12, batch_paragraphs=False):
+    for chunk_data in chunk_by_paragraph(test_text, 12, batch_paragraphs=True):
         chunks.append(chunk_data)
 
     assert len(chunks) == 3