From 5698ac70c6ac7169ebe4091704d701b749faf059 Mon Sep 17 00:00:00 2001 From: shiyu22 Date: Tue, 30 May 2023 18:42:50 +0800 Subject: [PATCH] Update README Signed-off-by: shiyu22 --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 03c31aa..2c95b41 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# Text Spliter +# Text Splitter *author: shiyu22* @@ -8,9 +8,9 @@ ### Description -**Text spliter** is used to split text into chunk lists. +**Text splitter** is used to split text into chunk lists. -> Refer to [Recursive Characters](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/recursive_text_splitter.html) for the operation of splitting text. +> Refer to [Text Splitters](https://python.langchain.com/en/latest/modules/indexes/text_splitters.html) for the operation of splitting text.
@@ -24,7 +24,7 @@ from towhee import pipe, ops, DataCollection p = ( pipe.input('url') .map('url', 'text', ops.text_loader()) - .flat_map('text', 'text', ops.text_spliter()) + .flat_map('text', 'text', ops.text_splitter()) .output('url', 'text') ) @@ -48,7 +48,7 @@ Create the operator via the following factory method ​ ***type***: str -​ The type of spliter, defaults to 'RecursiveCharacter'. You can set this parameter in ['[RecursiveCharacter](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/recursive_text_splitter.html)', '[Markdown](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/markdown.html)', '[PythonCode](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/python.html)', '[Character](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html#)', '[NLTK](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/nltk.html)', '[Spacy](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/spacy.html)', '[Tiktoken](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/tiktoken_splitter.html)', '[HuggingFace](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/huggingface_length_function.html)']. +​ The type of splitter, defaults to 'RecursiveCharacter'. You can set this parameter in ['[RecursiveCharacter](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/recursive_text_splitter.html)', '[Markdown](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/markdown.html)', '[PythonCode](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/python.html)', '[Character](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html#)', '[NLTK](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/nltk.html)', '[Spacy](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/spacy.html)', '[Tiktoken](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/tiktoken_splitter.html)', '[HuggingFace](https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/huggingface_length_function.html)']. ​ ***chunk_size***: int