All data added to the Cherry Studio knowledge base is stored locally. During the adding process, a copy of the document is placed in the Cherry Studio data storage directory.
After a document is added to the Cherry Studio knowledge base, the file is split into several chunks, and then these chunks are handed over to the embedding model for processing.
When using a large model for Q&A, the text chunks related to the question will be queried and handed over to the large language model for processing together.
If you have data privacy requirements, it is recommended to use a local embedding database and a local large language model.
