Zilliz, the company behind Milvus, also offers a fully managed cloud version of the platform for those that don’t want to build and maintain their own distributed instance. Zilliz Cloud automatically maintains data reliability and allows users to pay only for what they use.
Milvus cannot be installed or run on non-x86 platforms.
Your CPU must support one of the following instruction sets to run Milvus: SSE4.2, AVX, AVX2, AVX512. These are all x86-dedicated SIMD instruction sets.
-Theoretically, the maximum dataset size Milvus can handle is determined by the hardware it is run on, specifically system memory and storage:
-Milvus deals with two types of data, inserted data and metadata.
Inserted data, including vector data, scalar data, and collection-specific schema, are stored in persistent storage as incremental log. Milvus supports multiple object storage backends, including MinIO, AWS S3, Google Cloud Storage (GCS), Azure Blob Storage, Alibaba Cloud OSS, and Tencent Cloud Object Storage (COS).
Metadata are generated within Milvus. Each Milvus module has its own metadata that are stored in etcd.
@@ -41,17 +36,17 @@ title: Product FAQEntity primary keys must be non-negative 64-bit integers.
An insert operation must not exceed 1,024 MB in size. This is a limit imposed by gRPC.
No. If partitions for a search are specified, Milvus searches the specified partitions only.
-No. Milvus has varied behavior. Data must be loaded to memory before searching.
+It depends on what data is needed for search. All partitions potentially show up in search result must be loaded before searching.
load_partition() to load the intended partition(s) then specify partition(s) in the search() method call.load_collection() before calling search().load_partition() to load the intended partition(s) then specify partition(s) in the search() method call.load_collection() to load the whole collection including all partitions.Yes. If an index has been built for a collection by create_index() before, Milvus will automatically build an index for subsequently inserted vectors. However, Milvus does not build an index until the newly inserted vectors fill an entire segment and the newly created index file is separate from the previous one.
The IVF_FLAT index divides vector space into list clusters. At the default list value of 16,384, Milvus compares the distances between the target vector and the centroids of all 16,384 clusters to return probe nearest clusters. Milvus then compares the distances between the target vector and the vectors in the selected clusters to get the nearest vectors. Unlike IVF_FLAT, FLAT directly compares the distances between the target vector and every other vector.
When the total number of vectors approximately equals nlist, there is little distance between IVF_FLAT and FLAT in terms of calculation requirements and search performance. However, as the number of vectors exceeds nlist by a factor of two or more, IVF_FLAT begins to demonstrate performance advantages.
See Vector Index for more information.
-Milvus returns success when inserted data are loaded to the message queue. However, the data are not yet flushed to the disk. Then Milvus’ data node writes the data in the message queue to persistent storage as incremental logs. If flush() is called, the data node is forced to write all data in the message queue to persistent storage immediately.
Milvus returns success when inserted data are ingested to the message queue. However, the data are not yet flushed to the disk. Then Milvus’ data node writes the data in the message queue to persistent storage as incremental logs. If flush() is called, the data node is forced to write all data in the message queue to persistent storage immediately.
Normalization refers to the process of converting a vector so that its norm equals 1. If inner product is used to calculate vector similarity, vectors must be normalized. After normalization, inner product equals cosine similarity.
See Wikipedia for more information.
For normalized vectors, Euclidean distance (L2) is mathematically equivalent to inner product (IP). If these similarity metrics return different results, check to see if your vectors are normalized
@@ -67,7 +62,7 @@ title: Product FAQCurrent Milvus release does not support Apple M1 CPU directly. After Milvus 2.3, Milvus provides Docker images for the ARM64 architecture.
In current release, Milvus supports both INT64 and string.
Yes. You can deploy Milvus cluster with multiple nodes via Helm Chart on Kubernetes. Refer to Scale Guide for more instruction.
-Yes. When a query request comes, Milvus searches both incremental data and historical data by loading them into memory. Incremental data are in the growing segments, which are buffered in memory before they reach the threshold to be persisted in storage engine, while historical data are from the sealed segments that are stored in the object storage. Incremental data and historical data together constitute the whole dataset to search.
+When a search request comes, Milvus searches both incremental data and historical data. Incremental data are recent updates, they are stored in the growing segments, which are buffered in memory before they reach the threshold to be persisted in object storage and a more efficient index is built for them, while historical data are updates a while ago. They are in the sealed segments which have been persisted in the object storage. Incremental data and historical data together constitute the whole dataset for search. This design makes any data ingested to Milvus instantly searchable. For Milvus Distributed, there are more complex factors that decide when a record just ingested can show up in search result. Learn more nuance about that at consistency levels.
Yes. For queries on the same collection, Milvus concurrently searches the incremental and historical data. However, queries on different collections are conducted in series. Whereas the historical data can be an extremely huge dataset, searches on the historical data are relatively more time-consuming and essentially performed in series.
Data in MinIO is designed to remain for a certain period of time for the convenience of data rollback.
Yes. Kafka is supported in Milvus 2.1.0.