Kevin Hu
Kevin Hu
> What do you mean there are a lot of duplicate questions here? When I searched for cron_logger, Only I have this cron_logger problem. Are you talking about the number...
I discovered that onnx-runtime didn't support GPU well. So, if you want to try it, just remove the 'False' and let it use GPU.
Did it happend on demo site or locally deployed?
What kind of chunking method you want to define? And what kind of problem you want to solve?
-- We use visual model to parsing PDF, so it's slow. We're working on its speed. You can disable layout recognition for PDF in general parsing method. And this can...
Fixed. Pull the image infiniflow/ragflow-base:v2.0
If you deloyed LLM and ragflow locally, the data would go nowhere.
Please check those inference tools: Ollama/xinference/vllm.
In terms of parsing, we only need to assign an embedding model to knowledge base. So, what's the error message?