OneKe
OneKe
you can open file:dokit-front\src\store\modules\permission.js and modify method:loadView ` export const loadView = (view) => { return require(`@/views/${view}`).default } `
because redis is down，you can clone it then start it by yourself
@yingfeng @KevinHuSh It's urgent.
ERROR 38 Fail to bind embedding model: Model(BAAI/bge-large-zh-v1.5@BAAI@None) not authorized Traceback (most recent call last): File "/ragflow/rag/svr/task_executor.py", line 790, in do_handle_task embedding_model = LLMBundle(task_tenant_id, LLMType.EMBEDDING, llm_name=task_embedding_id, lang=task_language) File "/ragflow/api/db/services/llm_service.py", line...
@KevinHuSh I once doubted this issue too, but tests have confirmed that the key is valid.
@yongtenglei It was deployed directly using the mirror image, not via the source code, and no modifications were made.
@yongtenglei operation process: Before replacing the embedding model, I first selected all files, clicked "Re-parse", then quickly clicked "Cancel". I thought this would delete all existing data, so I went...
@buua436 Yes, I confirm that it can be used.
@KevinHuSh @yingfeng @buua436 @yongtenglei I have an extreme idea: what if we delete this user's index in Elasticsearch—would that allow switching to any embedding model?
@yongtenglei Then please tell me what to do. I have a large number of files that all use the vectors from BAAI/bge-large-zh-v1.5. If this issue isn’t resolved today, I’ll have...