Increase Your Vector Database Read Throughput with In-Memory Replicas

What this post added

Introduces the concept and implementation of in-memory replicas in Milvus 2.1. Explains replica groups, shard replicas, streaming replicas, historical replicas, and shard leaders. Details how enabling in-memory replicas boosts QPS and throughput by allowing multiple query nodes to serve search requests for the same data segment. Provides a Python code example for loading a collection with multiple replicas and a method to retrieve replica information.