updated chuck_size and overlap as they were too small
This commit is contained in:
@@ -52,7 +52,7 @@ def load_web_crawl(url):
|
|||||||
# docs_list = [item for sublist in docs for item in sublist]
|
# docs_list = [item for sublist in docs for item in sublist]
|
||||||
# Initialize a text splitter with specified chunk size and overlap
|
# Initialize a text splitter with specified chunk size and overlap
|
||||||
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
|
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
|
||||||
chunk_size=250, chunk_overlap=0
|
chunk_size=1000, chunk_overlap=200
|
||||||
)
|
)
|
||||||
# Split the documents into chunks
|
# Split the documents into chunks
|
||||||
return text_splitter.split_documents(docs)
|
return text_splitter.split_documents(docs)
|
||||||
|
|||||||
Reference in New Issue
Block a user