pengjunfeng11
commited on
Update code comments in ainsert method
Browse filesUpdate code comments in ainsert method. The original comment was cut off in the middle, not a complete sentence, and cannot be read
- lightrag/lightrag.py +2 -0
lightrag/lightrag.py
CHANGED
@@ -553,6 +553,7 @@ class LightRAG:
|
|
553 |
Args:
|
554 |
input: Single document string or list of document strings
|
555 |
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
|
|
|
556 |
split_by_character_only: if split_by_character_only is True, split the string by character only, when
|
557 |
split_by_character is None, this parameter is ignored.
|
558 |
ids: single string of the document ID or list of unique document IDs, if not provided, MD5 hash IDs will be generated
|
@@ -574,6 +575,7 @@ class LightRAG:
|
|
574 |
Args:
|
575 |
input: Single document string or list of document strings
|
576 |
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
|
|
|
577 |
split_by_character_only: if split_by_character_only is True, split the string by character only, when
|
578 |
split_by_character is None, this parameter is ignored.
|
579 |
ids: list of unique document IDs, if not provided, MD5 hash IDs will be generated
|
|
|
553 |
Args:
|
554 |
input: Single document string or list of document strings
|
555 |
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
|
556 |
+
chunk_token_size, it will be split again by token size.
|
557 |
split_by_character_only: if split_by_character_only is True, split the string by character only, when
|
558 |
split_by_character is None, this parameter is ignored.
|
559 |
ids: single string of the document ID or list of unique document IDs, if not provided, MD5 hash IDs will be generated
|
|
|
575 |
Args:
|
576 |
input: Single document string or list of document strings
|
577 |
split_by_character: if split_by_character is not None, split the string by character, if chunk longer than
|
578 |
+
chunk_token_size, it will be split again by token size.
|
579 |
split_by_character_only: if split_by_character_only is True, split the string by character only, when
|
580 |
split_by_character is None, this parameter is ignored.
|
581 |
ids: list of unique document IDs, if not provided, MD5 hash IDs will be generated
|