Snify89
Snify89
Would love to see this implemented as well. Thank you for considering
I am sure, there must be a connection issue. Ragflow (docker) has a built in network. Try entering the ragflow-server docker container with docker exec -it ragflow-server (or your container...
> The prompt is [here](https://github.com/infiniflow/ragflow/blob/251592eeebd897ae48209940e39eeb75a04a821e/api/db/services/dialog_service.py#L473). LLM has already been told to be in language of the chunk text. @KevinHuSh Thank you for the position in the code. The problem is,...
> my changes have not been merged into the llama.cpp official yet, and you may need to wait until the merge. Thank you for your contribution! Do you do a...
It might be an incompatible file which has security (e.g. password/signature) or too many pixels (e.g. pixel bomb vector), broken/incompatible exif data, etc. PDFs are a mess actually and unfortunately...
Do you have an estimate on how much (k/M)bytes it "leaks" per parsed document?
Could you test this with/without OCR layer embedded in the file? Is it PDF only? Does it also occur when using deepdoc (standalone) only?
>  Hi. The image is for infinity and not ragflow. Please check again, thanks
> Hi, > > Is there an issue with `non-stream` mode? We have just fixed a problem with stream mode. We typically test our API using Postman and curl and...