Create a Collection

This topic describes how to create a collection in Milvus.

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

The following example builds a two-shard collection named book, with a primary key field named book_id, an INT64 scalar field named word_count, and a two-dimensional floating-point vector field named book_intro. Real applications will likely use much higher dimensional vectors than the example.

Prepare Schema

First, prepare necessary parameters, including field schema, collection schema, and collection name.

from pymilvus import CollectionSchema, FieldSchema, DataType
book_id = FieldSchema(
  name="book_id", 
  dtype=DataType.INT64, 
  is_primary=True, 
)
book_name = FieldSchema(
  name="book_name", 
  dtype=DataType.VARCHAR, 
  max_length=200,
)
word_count = FieldSchema(
  name="word_count", 
  dtype=DataType.INT64,  
)
book_intro = FieldSchema(
  name="book_intro", 
  dtype=DataType.FLOAT_VECTOR, 
  dim=2
)
schema = CollectionSchema(
  fields=[book_id, book_name, word_count, book_intro], 
  description="Test book search"
)
collection_name = "book"

const params = {
  collection_name: "book",
  description: "Test book search",
  fields: [
    {
      name: "book_intro",
      description: "",
      data_type: 101,  // DataType.FloatVector
      type_params: {
        dim: "2",
      },
    },
    {
      name: "book_id",
      data_type: 5,   //DataType.Int64
      is_primary_key: true,
      description: "",
    },
    {
      name: "word_count",
      data_type: 5,    //DataType.Int64
      description: "",
    },
  ],
};

var (
        collectionName = "book"
    )
schema := &entity.Schema{
  CollectionName: collectionName,
  Description:    "Test book search",
  Fields: []*entity.Field{
    {
      Name:       "book_id",
      DataType:   entity.FieldTypeInt64,
      PrimaryKey: true,
      AutoID:     false,
    },
    {
      Name:       "word_count",
      DataType:   entity.FieldTypeInt64,
      PrimaryKey: false,
      AutoID:     false,
    },
    {
      Name:     "book_intro",
      DataType: entity.FieldTypeFloatVector,
      TypeParams: map[string]string{
          "dim": "2",
      },
    },
  },
}

FieldType fieldType1 = FieldType.newBuilder()
        .withName("book_id")
        .withDataType(DataType.Int64)
        .withPrimaryKey(true)
        .withAutoID(false)
        .build();
FieldType fieldType2 = FieldType.newBuilder()
        .withName("word_count")
        .withDataType(DataType.Int64)
        .build();
FieldType fieldType3 = FieldType.newBuilder()
        .withName("book_intro")
        .withDataType(DataType.FloatVector)
        .withDimension(2)
        .build();
CreateCollectionParam createCollectionReq = CreateCollectionParam.newBuilder()
        .withCollectionName("book")
        .withDescription("Test book search")
        .withShardsNum(2)
        .addFieldType(fieldType1)
        .addFieldType(fieldType2)
        .addFieldType(fieldType3)
        .build();

create collection -c book -f book_id:INT64:book_id -f word_count:INT64:word_count -f book_intro:FLOAT_VECTOR:2 -p book_id

curl -X 'POST' \
  'http://localhost:9091/api/v1/collection' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
    "collection_name": "book",
    "schema": {
      "autoID": false,
      "description": "Test book search",
      "fields": [
        {
          "name": "book_id",
          "description": "book id",
          "is_primary_key": true,
          "autoID": false,
          "data_type": 5
        },
        {
          "name": "word_count",
          "description": "count of words",
          "is_primary_key": false,
          "data_type": 5
        },
        {
          "name": "book_intro",
          "description": "embedded vector of book introduction",
          "data_type": 101,
          "is_primary_key": false,
          "type_params": [
            {
              "key": "dim",
              "value": "2"
            }
          ]
        }
      ],
      "name": "book"
    }
  }'

{}

Create a collection with the schema

Then, create a collection with the schema you specified above.

from pymilvus import Collection
collection = Collection(
    name=collection_name, 
    schema=schema, 
    using='default', 
    shards_num=2,
    )

await milvusClient.collectionManager.createCollection(params);

err = milvusClient.CreateCollection(
    context.Background(), // ctx
    schema,
    2, // shardNum
)
if err != nil {
    log.Fatal("failed to create collection:", err.Error())
}

milvusClient.createCollection(createCollectionReq);

# Follow the previous step.

# Follow the previous step.

Limits

What’s next

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