Update functions.py
Browse files- functions.py +1 -1
functions.py
CHANGED
@@ -127,7 +127,7 @@ def process_corpus(corpus, _tokenizer, title, embedding_model, chunk_size=200, o
|
|
127 |
|
128 |
'''Process text for Semantic Search'''
|
129 |
|
130 |
-
text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(_tokenizer,chunk_size=chunk_size,chunk_overlap=overlap)
|
131 |
|
132 |
texts = text_splitter.split_text(corpus)
|
133 |
|
|
|
127 |
|
128 |
'''Process text for Semantic Search'''
|
129 |
|
130 |
+
text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(_tokenizer,chunk_size=chunk_size,chunk_overlap=overlap,separator='.')
|
131 |
|
132 |
texts = text_splitter.split_text(corpus)
|
133 |
|