From 7eda0fff7438ee521e745c4e89f9dd6b2118379e Mon Sep 17 00:00:00 2001 From: Rodrigo Nader Date: Sat, 30 Mar 2024 19:06:23 -0300 Subject: [PATCH] Update SplitTextComponent in langflow/helpers*** --- .../base/langflow/components/helpers/SplitText.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/src/backend/base/langflow/components/helpers/SplitText.py b/src/backend/base/langflow/components/helpers/SplitText.py index ac8c6fe29..4d73f7f42 100644 --- a/src/backend/base/langflow/components/helpers/SplitText.py +++ b/src/backend/base/langflow/components/helpers/SplitText.py @@ -9,7 +9,7 @@ from langchain_core.documents import Document from langflow.interface.custom.custom_component import CustomComponent from langflow.schema import Record from langflow.field_typing import Text -from langflow.utils.util import unescape_string +from langflow.utils.util import build_loader_repr_from_records, unescape_string class SplitTextComponent(CustomComponent): @@ -25,18 +25,18 @@ class SplitTextComponent(CustomComponent): }, "separators": { "display_name": "Separators", - "info": 'The characters to split on.\nIf left empty defaults to [" "].', + "info": 'The characters to split on. Defaults to [" "].', "is_list": True, }, "chunk_size": { - "display_name": "Chunk Size", - "info": "The maximum length of each chunk.", + "display_name": "Max Chunk Size", + "info": "The maximum length (in number of characters) of each chunk.", "field_type": "int", "value": 1000, }, "chunk_overlap": { "display_name": "Chunk Overlap", - "info": "The amount of overlap between chunks.", + "info": "The amount of character overlap between chunks.", "field_type": "int", "value": 200, }, @@ -54,6 +54,7 @@ class SplitTextComponent(CustomComponent): chunk_overlap: Optional[int] = 200, recursive: bool = False, ) -> list[Record]: + separators = [unescape_string(x) for x in separators] # Make sure chunk_size and chunk_overlap are ints