[Question]: I have a few questions about RagFlow's clustering capabilities that I'd like to ask

[myplxdm]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (Language Policy).
• Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) (Language Policy).
• Please do not modify this template :) and fill in all the required fields.

Describe your problem

1. Does RagFlow support clustering?
2. If clustering is supported, how does it save a knowledge base file when uploaded?
3. If my knowledge base is very large, say 1TB, would implementing multiple vector databases require running multiple RagFlow Docker instances, rather than just a single Infinity or other service?

[JinHai-CN]

RAGFlow server and task executor are stateless. Except RAGFlow server and task executor, RAGFlow service also depends on mysql / elasticsearch(or infinity) / minio which will store the data (state). You may expand the capacity of these components in your case.