----------------------
To increase the chunk size in LlamaIndex, you need to adjust the
chunk_size parameter in the
Settings class from the
llama_index.core module. Here is an example of how to do it:
from llama_index.core import Settings
# initialize settings (set chunk size)
Settings.chunk_size = 1024 # You can set this to any value you want
This setting will be used when documents are ingested into an index, where they are split into chunks of the specified size.
Please note that changing the chunk size will change the embeddings that are calculated. A smaller chunk size means the embeddings are more precise, while a larger chunk size means that the embeddings may be more general, but can miss fine-grained details.
For more information, you can refer to the
LlamaIndex documentation () and
this guide on optimizing basic strategies ().
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------
