Category "milvus"

What is included in the ‘standalone’ vs ‘cluster’ Milvus deployments?

What is included in the ‘standalone’ vs ‘cluster’ Milvus deployments? Standalone makes it sound like it is a single instance, but as far

Does milvus auto-flush inserted data to object storage? or do we have to manually call flush?

I used the milvus1.x version in the past. After I insert data, I need to call the flush interface to ensure that the data is placed on the disk, so as to ensure

Milvus 1.1.1 only continues to query, memory usage continues to grow, from 4g to 20GB, what might be the cause?

My dataset: 1M 768d Index: ivf_pq,nlist=4096,m=12 Operation: Only search, without insert and delete

If I set auto_id=true, then I insert data into milvus concurrently. Will the id in Milvus be repeated?

If I set auto_id=true, then I insert data into milvus concurrently. Will the id in Milvus be repeated? I am using Milvus2.0.

After milvus is started, where is the newly inserted data stored?

I follow this link to start Milvus1.1.1. After I started it successfully, I inserted some data into it. But I don't know where my data is saved.

The distributed version of Milvus 2.0 loads data without load balancing

For the distributed version of Milvus 2.0.2, I tested to increase the number of querynodes online. It seems that the data will not be load balanced, and the mem

All else held equal, which is the faster querying option: Milvus, RocksDB, or Apache HBase

I have a requirement to store billions of records (with capacity up to one trillion records) in a database (total size is in terms of petabytes). The records ar