writinwaters
writinwaters
Issue fixed in PR #2041
This setting has been removed in v0.17.2. Apologies that this change was only reflected in the dev documentation.
Hiya, {knowledge} is a hard-coded variable, which refers to all chunks in your chosen knowledge base(s). In other words, with this prompt, chunks from your chosen knowledge base(s) will be...
Hiya, RAGFlow's open-source version only allows your team members to access and [share your knowledge base](https://ragflow.io/docs/dev/manage_team_members). Chats and agents cannot be shared. A team member can view knowledge bases created...
Hate to say it, as far as I know, complicated team sharing logic will only be supported in the Enterprise edition. But team members *can* configure knowledge bases with the...
Hope this could help: https://ragflow.io/docs/dev/accelerate_question_answering
[Question]: What type of GPU and how many GPUs are recommended to fasten the speed of parsing files?
Create a knowledge base is not time-consuming; parsing file is. Here are some tips: https://ragflow.io/docs/dev/accelerate_doc_indexing Or, you can use docker-compose-gpu.yml to start your service. This accelerates DeepDoc tasks using GPU,...
[Question]: What type of GPU and how many GPUs are recommended to fasten the speed of parsing files?
You are right in that embedding is not the only stage that takes time. You toggled on RAPTOR, and this is another time consumer. BTW, embedding models are for *offline*...
[Question]: What type of GPU and how many GPUs are recommended to fasten the speed of parsing files?
Yes, you are right.
[Question]: What type of GPU and how many GPUs are recommended to fasten the speed of parsing files?
Thanks @yuzhichang for sharing the story behind this. @said-what-sakula You can take a look at Feature 5 of RAGFlow's latest release notes: https://ragflow.io/docs/dev/release_notes#v0170