I am currently using pymilvus 2.4.3 and my data contains sparse vector.

I’m using Python with LangChain to transform .txt files into chunks, where each chunk contains 512 tokens.

image is existing schema from zilliz, message.txt is error log, sample_input.txt is sample input text.
sample input langchain document object

I can’t access milvus attu. ForbiddenError.
and I was using attu 2.3.2 and then upgraded to attu 2.4.2.
I haven’t set anything like User, Role, etc.

We have a cluster deployment of Milvus on the k8s and our dataset sizes are of the order of a 150 million. The querynodes are distributed across 16 replicas with 40G of memory each. The current bottleneck for us in the partition load times and we exploring ways to improve the load times. We were referring to https://milvus.io/docs/chunk_cache.md and tried setting this up in our deployment. However, we do not see any noticeable improvements in the load times and from the logs, there is not indication that the chunk cache is being loaded. There are a couple of questions we have in this area:

Milvus-standalone worked well when my MacOS was with 12.3.
When I upgrade MacOS to 12.5.1, I cannot install Milvus-standalone correctly.
As you see below, Milvus-standalone is always exited (2).

I am trying to install milvus db with milvus operator on my EKS cluster. I have a running milvus operator pod. The logs of pod doesnot show any error. But when I try to create a milvus standalone cluster using this command : kubectl apply -f https://raw.githubusercontent.com/zilliztech/milvus-operator/main/config/samples/milvus_default.yaml

Can someone please verify the keys I am using for Node SDK for milvus?

I am using the Attu client to manage the data from Milvus and all the data looks good inside.

I’ve got a bunch of logs that look like this