The Architecture Handbook for Milvus Vector Database
by Yudong Cai, Jeremy Zhu, Xuan Yang, Bang Fu
7
Reading Data in Milvus
In Chapter 6, we detailed the process of writing data into Milvus. This chapter shifts our focus to the other side of the equation: how to efficiently retrieve that data.
To understand the read path, we must revisit the core design principle from Chapter 5: read-write separation. This separation is crucial because it endows the read path with a powerful dual capability. On one hand, it has the ability to provide stable, high-performance queries on optimized, persistent historical data, completely unaffected by complex tasks on the write path, such as segment state transitions, compaction, or index building.
On the other hand, it also possesses the flexibility to provide near-real-time visibility for the new data. This ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access