recommended value for chunk_size and chunk_overlap

[jsmith173]

What is the recommended value for chunk_size and chunk_overlap when calling RecursiveCharacterTextSplitter?

[dosubot[bot]]

The recommended values for chunk_size and chunk_overlap when calling RecursiveCharacterTextSplitter are not explicitly stated in the provided document. However, the example usage sets chunk_size to 250 and chunk_overlap to 30.

from langchain_text_splitters import RecursiveCharacterTextSplitter

chunk_size = 250
chunk_overlap = 30
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=chunk_size, 
    chunk_overlap=chunk_overlap
)

^[1][2][3]

To continue talking to Dosu, mention @dosu.

[jsmith173]

@dosu I have an other question.
I have the following code

			loader = WebBaseLoader(self.config['links'])
			data = loader.load()

How could I print 'data' as pure text?

[dosubot[bot]]

You can print data as pure text by iterating through the loaded data and printing each element. Here's how you can do it:

loader = WebBaseLoader(self.config['links'])
data = loader.load()

for item in data:
    print(item)

This will print each item in data to the console. If data contains objects, you might need to access specific attributes or methods to get the text representation.

To continue talking to Dosu, mention @dosu.