Error in knowledge base retrieval after upgrading to 1.10.1

Discussion
1

After upgrading our version to 1.10.1, the previously working knowledge base retrieval has started encountering retrieval errors. Earlier, we encountered a similar GRPC error as below:

Query call with protocol GRPC search failed with message extract target vectors: class Vector_index_57c0bdf2_49ab_4f8d_9207_870d6352276c_Node does not have named vector default configured. Available named vectors map[].

Following forum posts, we switched the embedding model. However, we still occasionally encounter the following error regardless of whether we use Huawei Cloud’s bge-m3 or Sillicon Flow’s BAAI/bge-m3:

req_id: 6c339af6ca PluginInvokeError: {“args”:{“description”:“[models] Error: 400 Client Error: Bad Request for url: https://api.modelarts-maas.com/v1/rerank"},“error_type”:“InvokeError”,“message”:"[models] Error: 400 Client Error: Bad Request for url: https://api.modelarts-maas.com/v1/rerank”}

Could you please advise if there are any other solutions besides downgrading to version 1.9.1? We’ve already invested significant effort in workflows and knowledge bases, and switching large models one by one is quite cumbersome. Thank you!

2

Migration needed due to the upgrade of Weaviate.
Refer to the following issue.