writinwaters

Results 37 comments of writinwaters

> Can RAPTOR and Extracting knowledge graph (GraphRAG) also run on GPU to accelerate? > > > You are right in that embedding is not the only stage that takes...

Could you use the keywords in the diagram to search for the related chunk?

> Perhaps i should choose "Book" Chunk method to parse the PDF file because it is an e-book. You don't have to change chunk method. Check if the diagram is...

RAGFlow supports adding metadata to individual files. See here: https://ragflow.io/docs/dev/set_metada. This is a feature introduced in v0.16.0: https://ragflow.io/docs/dev/release_notes#v0160

Hiya, what's your RAGFlow version? v0.17.0 supports embedding Begin component with global variables into webpage. Note that *currently* Begin component with file variables cannot be embedded into webpage.

Ugh. Apologies. This feature is not on the roadmap. As a workaround, you can save the HTML files. They can be previewed during an AI chat.

Hi @yangxg A v0.16.0 feature called tag knowledge base allows you to bulk tag chunks using the LLM. I haven't gotten around to creating a guide for it. Will link...

The api works well in client-server mode, but not in python module mode (local mode).

Please note abs() is implemented in output(), but not yet implemented in filter().