Spaces:
Sleeping
Sleeping
Commit ·
e419601
1
Parent(s): 3f598bc
added utilities folder
Browse files- utils/__pycache__/split.cpython-310.pyc +0 -0
- utils/ingest.py +0 -0
- utils/split.py +4 -0
utils/__pycache__/split.cpython-310.pyc
ADDED
|
Binary file (541 Bytes). View file
|
|
|
utils/ingest.py
ADDED
|
File without changes
|
utils/split.py
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
|
| 3 |
+
def split(text, chunk_size=1000):
|
| 4 |
+
return (text[0+i:chunk_size+i] for i in range(0, len(text), chunk_size))
|