jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

📝 docs(LanguageRecursiveTextSplitter.py): update documentation link to point to the correct URL

Browse source 
🔨 refactor(LanguageRecursiveTextSplitter.py): change type hints for the 'documents' parameter from Document to list[Document] and change return type from Document to list[Document] to improve clarity and consistency
🔨 refactor(LanguageRecursiveTextSplitter.py): change type hints for the 'chunk_overlap' parameter from Optional[int] to Optional[str] and handle conversion to int to improve flexibility and error handling
🔨 refactor(LanguageRecursiveTextSplitter.py): change type hints for the 'chunk_size' parameter from Optional[int] to Optional[str] and handle conversion to int to improve flexibility and error handling
🔨 refactor(RecursiveCharacterTextSplitter.py): change type hints for the 'documents' parameter from Document to list[Document] and change return type from Document to list[Document] to improve clarity and consistency
🔨 refactor(RecursiveCharacterTextSplitter.py): change type hints for the 'separators' parameter from Optional[str] to Optional[list[str]] and handle conversion to list of escaped characters to improve flexibility and error handling
🔨 refactor(RecursiveCharacterTextSplitter.py): change type hints for the 'chunk_overlap' parameter from Optional[int] to Optional[str] and handle conversion to int to improve flexibility and error handling
🔨 refactor(RecursiveCharacterTextSplitter.py): change type hints for the 'chunk_size' parameter from Optional[int] to Optional[str] and handle conversion to int to improve flexibility and error handling
This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-08-24 22:52:16 -03:00
commit a28df1f08f
2 changed files with 11 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/backend/langflow/components/textsplitters/LanguageRecursiveTextSplitter.py
View file

@ -8,7 +8,7 @@ from langflow.utils.util import build_loader_repr_from_documents
class LanguageRecursiveTextSplitterComponent(CustomComponent):
display_name: str = "Language Recursive Text Splitter"
description: str = "Split text into chunks of a specified length based on language."
documentation: str = "https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter"
documentation: str = "https://docs.langflow.org/components/text-splitters#languagerecursivetextsplitter"
def build_config(self):
options = [x.value for x in Language]
@ -46,11 +46,11 @@ class LanguageRecursiveTextSplitterComponent(CustomComponent):
def build(
self,
documents: Document,
documents: list[Document],
chunk_size: Optional[int] = 1000,
chunk_overlap: Optional[int] = 200,
separator_type: Optional[str] = "Python",
) -> Document:
) -> list[Document]:
"""
Split text into chunks of a specified length.
@ -66,14 +66,11 @@ class LanguageRecursiveTextSplitterComponent(CustomComponent):
from langchain.text_splitter import RecursiveCharacterTextSplitter
# Make sure chunk_size and chunk_overlap are ints
try:
if isinstance(chunk_size, str):
chunk_size = int(chunk_size)
if isinstance(chunk_overlap, str):
chunk_overlap = int(chunk_overlap)
except Exception as e:
raise ValueError(
"chunk_size and chunk_overlap must be integers."
" Received chunk_size={chunk_size} and chunk_overlap={chunk_overlap}."
) from e
splitter = RecursiveCharacterTextSplitter.from_language(
language=Language(separator_type),
chunk_size=chunk_size,

14
src/backend/langflow/components/textsplitters/RecursiveCharacterTextSplitter.py
View file

@ -36,11 +36,11 @@ class RecursiveCharacterTextSplitterComponent(CustomComponent):
def build(
self,
documents: Document,
separators: Optional[str] = None,
documents: list[Document],
separators: Optional[list[str]] = None,
chunk_size: Optional[int] = 1000,
chunk_overlap: Optional[int] = 200,
) -> Document:
) -> list[Document]:
"""
Split text into chunks of a specified length.
@ -63,14 +63,10 @@ class RecursiveCharacterTextSplitterComponent(CustomComponent):
separators = [x.encode().decode("unicode-escape") for x in separators]
# Make sure chunk_size and chunk_overlap are ints
try:
if isinstance(chunk_size, str):
chunk_size = int(chunk_size)
if isinstance(chunk_overlap, str):
chunk_overlap = int(chunk_overlap)
except Exception as e:
raise ValueError(
"chunk_size and chunk_overlap must be integers."
" Received chunk_size={chunk_size} and chunk_overlap={chunk_overlap}."
) from e
splitter = RecursiveCharacterTextSplitter(
separators=separators,
chunk_size=chunk_size,