tigflank

@dosu A key question is that the number of tokens should be less than or equal to the number of characters, regardless of the tokenization strategy. My understanding is that...

@dosu Interestingly, the problem is the opposite of what one might expect. In my test, 1900 Chinese characters (“一二三四五六七八九\n”*190) were truncated. As observed from my post, the segment length retained...

Currently, I am indeed very menbility(puzzled). I have tested two more cases. In both cases, I used the `bge-large-zh` model for tokenization tests, and they were both tokenized at the...

It feels like the Python execution and UI operations are disconnected. The UI operation makes it very convenient to upload documents directly, but in reality, I need to customize many...

@Exploding-Soda I know how to proceed now. I just need to move all the files generated after executing Python into the subdirectory `rag_storage`. I will continue testing functions like `rag.create_entity`.

@Exploding-Soda When I upload documents separately using the endpoint (starting `lightrag-server` in the project directory `/data/github/LightRAG/znkf`), everything works fine, and the correct KG is constructed. 👍 However, when I use...

> if you have variable windows in the APP ,you must in the chatflow not workflow,I am sure you are using the chatflow. @su37sm No, in fact, I am using...