Create a Partition

This topic describes how to create a partition in Milvus.

Milvus allows you to divide the bulk of vector data into a small number of partitions. Search and other operations can then be limited to one partition to improve the performance.

A collection consists of one or more partitions. While creating a new collection, Milvus creates a default partition _default. See Glossary - Partition for more information.

The following example builds a partition novel in the collection book.

from pymilvus import Collection
collection = Collection("book")      # Get an existing collection.
collection.create_partition("novel")

await milvusClient.partitionManager.createPartition({
  collection_name: "book",
  partition_name: "novel",
});

err := milvusClient.CreatePartition(
  context.Background(),   // ctx
  "book",                 // CollectionName
  "novel"                 // partitionName
)
if err != nil {
  log.Fatal("failed to create partition:", err.Error())
}

milvusClient.createPartition(
  CreatePartitionParam.newBuilder()
    .withCollectionName("book")
    .withPartitionName("novel")
    .build()
);

create partition -c book -p novel

curl -X 'POST' \
  'http://localhost:9091/api/v1/partition' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "collection_name": "book",
    "partition_name": "novel"
  }'

Limits

What’s next

• Learn more basic operations of Milvus:
  • Insert data into Milvus
  • Build an index for vectors
  • Conduct a vector search
  • Conduct a hybrid search