Build an Index

Milvus Docs 需要你的帮助

本文档暂时没有中文版本，欢迎你成为社区贡献者，协助中文技术文档的翻译。
你可以通过页面右边的编辑按钮直接贡献你的翻译。更多详情，参考贡献指南。如需帮助，你可以提交 GitHub Issue。

This topic describes how to build an index for vectors in Milvus.

Vector indexes are an organizational unit of metadata used to accelerate vector similarity search. Without index built on vectors, Milvus will perform a brute-force search by default.

See Vector Index for more information about mechanism and varieties of vector indexes.

Current release of Milvus only supports index on vector field. Future releases will support index on scalar field.
By default, Milvus does not index a segment with less than 1,024 rows. To change this parameter, configure rootCoord.minSegmentSizeToEnableIndex in milvus.yaml.

The following example builds a 1024-cluster IVF_FLAT index with Euclidean distance (L2) as the similarity metrics. You can choose the index and metrics that suit your scenario. See Similarity Metrics for more information.

Prepare index parameter

Prepare the index parameters.

Python Java GO Node.js CLI

index_params = {
        "metric_type":"L2",
        "index_type":"IVF_FLAT",
        "params":{"nlist":1024}
    }

const index_params = {
  metric_type: "L2",
  index_type: "IVF_FLAT",
  params: JSON.stringify({ nlist: 1024 }),
};

idx, err := entity.NewIndexIvfFlat(   // NewIndex func
    entity.L2,                        // metricType
    1024,                             // ConstructParams
)
if err != nil {
    log.Fatal("fail to create ivf flat index parameter:", err.Error())
}

final IndexType INDEX_TYPE = IndexType.IVF_FLAT;   // IndexType
final String INDEX_PARAM = "{\"nlist\":1024}";     // ExtraParam

create index

Collection name (book): book

The name of the field to create an index for (book_intro): book_intro

Index type (FLAT, IVF_FLAT, IVF_SQ8, IVF_PQ, RNSG, HNSW, ANNOY): IVF_FLAT

Index metric type (L2, IP, HAMMING, TANIMOTO): L2

Index params nlist: 1024

Timeout []:

Parameter Description Options

Parameter	Description	Options
`metric_type`	Type of metrics used to measure similarity of vectors.	For floating point vectors: `L2` (Euclidean distance) `IP` (Inner product) For binary vectors: `JACCARD` (Jaccard distance) `TANIMOTO` (Tanimoto distance) `HAMMING` (Hamming distance) `SUPERSTRUCTURE` (Superstructure) `SUBSTRUCTURE` (Substructure)
`index_type`	Type of index used to accelerate the vector search.	For floating point vectors: `FLAT` (FLAT) `IVF_FLAT` (IVF_FLAT) `IVF_SQ8` (IVF_SQ8) `IVF_PQ` (IVF_PQ) `HNSW` (HNSW) `ANNOY` (ANNOY) `RHNSW_FLAT` (RHNSW_FLAT) `RHNSW_PQ` (RHNSW_PQ) `RHNSW_SQ` (RHNSW_SQ) For binary vectors: `BIN_FLAT` (BIN_FLAT) `BIN_IVF_FLAT` (BIN_IVF_FLAT)
`params`	Building parameter(s) specific to the index.	See Vector Index for more information.

metric_type

Type of metrics used to measure similarity of vectors.

For floating point vectors:

L2 (Euclidean distance)
IP (Inner product)

For binary vectors:

JACCARD (Jaccard distance)
TANIMOTO (Tanimoto distance)
HAMMING (Hamming distance)
SUPERSTRUCTURE (Superstructure)
SUBSTRUCTURE (Substructure)

index_type

Type of index used to accelerate the vector search.

For floating point vectors:

FLAT (FLAT)
IVF_FLAT (IVF_FLAT)
IVF_SQ8 (IVF_SQ8)
IVF_PQ (IVF_PQ)
HNSW (HNSW)
ANNOY (ANNOY)
RHNSW_FLAT (RHNSW_FLAT)
RHNSW_PQ (RHNSW_PQ)
RHNSW_SQ (RHNSW_SQ)

For binary vectors:

BIN_FLAT (BIN_FLAT)
BIN_IVF_FLAT (BIN_IVF_FLAT)

params Building parameter(s) specific to the index. See Vector Index for more information.

Parameter Description Option

Parameter	Description	Option
`metric_type`	Type of metrics used to measure similarity of vectors.	For floating point vectors: `L2` (Euclidean distance) `IP` (Inner product) For binary vectors: `JACCARD` (Jaccard distance) `TANIMOTO` (Tanimoto distance) `HAMMING` (Hamming distance) `SUPERSTRUCTURE` (Superstructure) `SUBSTRUCTURE` (Substructure)
`index_type`	Type of index used to accelerate the vector search.	For floating point vectors: `FLAT` (FLAT) `IVF_FLAT` (IVF_FLAT) `IVF_SQ8` (IVF_SQ8) `IVF_PQ` (IVF_PQ) `HNSW` (HNSW) `ANNOY` (ANNOY) `RHNSW_FLAT` (RHNSW_FLAT) `RHNSW_PQ` (RHNSW_PQ) `RHNSW_SQ` (RHNSW_SQ) For binary vectors: `BIN_FLAT` (BIN_FLAT) `BIN_IVF_FLAT` (BIN_IVF_FLAT)
`params`	Building parameter(s) specific to the index.	See Vector Index for more information.

metric_type

Type of metrics used to measure similarity of vectors.

For floating point vectors:

L2 (Euclidean distance)
IP (Inner product)

For binary vectors:

JACCARD (Jaccard distance)
TANIMOTO (Tanimoto distance)
HAMMING (Hamming distance)
SUPERSTRUCTURE (Superstructure)
SUBSTRUCTURE (Substructure)

index_type

Type of index used to accelerate the vector search.

For floating point vectors:

FLAT (FLAT)
IVF_FLAT (IVF_FLAT)
IVF_SQ8 (IVF_SQ8)
IVF_PQ (IVF_PQ)
HNSW (HNSW)
ANNOY (ANNOY)
RHNSW_FLAT (RHNSW_FLAT)
RHNSW_PQ (RHNSW_PQ)
RHNSW_SQ (RHNSW_SQ)

For binary vectors:

BIN_FLAT (BIN_FLAT)
BIN_IVF_FLAT (BIN_IVF_FLAT)

params Building parameter(s) specific to the index. See Vector Index for more information.

Parameter Description Options

Parameter	Description	Options
`NewIndex func`	Function to create entity.Index according to different index types.	For floating point vectors: `NewIndexFlat` (FLAT) `NewIndexIvfFlat` (IVF_FLAT) `NewIndexIvfSQ8` (IVF_SQ8) `NewIndexIvfPQ` (RNSG) `NewIndexRNSG` (HNSW) `NewIndexHNSW` (HNSW) `NewIndexANNOY` (ANNOY) `NewIndexRHNSWFlat` (RHNSW_FLAT) `NewIndexRHNSW_PQ` (RHNSW_PQ) `NewIndexRHNSW_SQ` (RHNSW_SQ) For binary vectors: `NewIndexBinFlat` (BIN_FLAT) `NewIndexBinIvfFlat` (BIN_IVF_FLAT)
`metricType`	Type of metrics used to measure similarity of vectors.	For floating point vectors: `L2` (Euclidean distance) `IP` (Inner product) For binary vectors: `JACCARD` (Jaccard distance) `TANIMOTO` (Tanimoto distance) `HAMMING` (Hamming distance) `SUPERSTRUCTURE` (Superstructure) `SUBSTRUCTURE` (Substructure)
`ConstructParams`	Building parameter(s) specific to the index.	See Vector Index for more information.

NewIndex func

Function to create entity.Index according to different index types.

For floating point vectors:

NewIndexFlat (FLAT)
NewIndexIvfFlat (IVF_FLAT)
NewIndexIvfSQ8 (IVF_SQ8)
NewIndexIvfPQ (RNSG)
NewIndexRNSG (HNSW)
NewIndexHNSW (HNSW)
NewIndexANNOY (ANNOY)
NewIndexRHNSWFlat (RHNSW_FLAT)
NewIndexRHNSW_PQ (RHNSW_PQ)
NewIndexRHNSW_SQ (RHNSW_SQ)

For binary vectors:

NewIndexBinFlat (BIN_FLAT)
NewIndexBinIvfFlat (BIN_IVF_FLAT)

metricType

Type of metrics used to measure similarity of vectors.

For floating point vectors:

L2 (Euclidean distance)
IP (Inner product)

For binary vectors:

JACCARD (Jaccard distance)
TANIMOTO (Tanimoto distance)
HAMMING (Hamming distance)
SUPERSTRUCTURE (Superstructure)
SUBSTRUCTURE (Substructure)

ConstructParams Building parameter(s) specific to the index. See Vector Index for more information.

Parameter Description Options

Parameter	Description	Options
`IndexType`	Type of index used to accelerate the vector search.	For floating point vectors: `FLAT` (FLAT) `IVF_FLAT` (IVF_FLAT) `IVF_SQ8` (IVF_SQ8) `IVF_PQ` (IVF_PQ) `HNSW` (HNSW) `ANNOY` (ANNOY) `RHNSW_FLAT` (RHNSW_FLAT) `RHNSW_PQ` (RHNSW_PQ) `RHNSW_SQ` (RHNSW_SQ) For binary vectors: `BIN_FLAT` (BIN_FLAT) `BIN_IVF_FLAT` (BIN_IVF_FLAT)
`ExtraParam`	Building parameter(s) specific to the index.	See Vector Index for more information.

IndexType

Type of index used to accelerate the vector search.

For floating point vectors:

FLAT (FLAT)
IVF_FLAT (IVF_FLAT)
IVF_SQ8 (IVF_SQ8)
IVF_PQ (IVF_PQ)
HNSW (HNSW)
ANNOY (ANNOY)
RHNSW_FLAT (RHNSW_FLAT)
RHNSW_PQ (RHNSW_PQ)
RHNSW_SQ (RHNSW_SQ)

For binary vectors:

BIN_FLAT (BIN_FLAT)
BIN_IVF_FLAT (BIN_IVF_FLAT)

ExtraParam Building parameter(s) specific to the index. See Vector Index for more information.

Option	Description
--help	Displays help for using the command.

Build index

Build the index by specifying the vector field name and index parameters.

Python Java GO Node.js CLI

from pymilvus import Collection
collection = Collection("book")      # Get an existing collection.
collection.create_index(
    field_name="book_intro", 
    index_params=index_params
    )

Status(code=0, message='')

await milvusClient.indexManager.createIndex({
  collection_name: "book",
  field_name: "book_intro",
  extra_params: index_params,
});

err = milvusClient.CreateIndex(
    context.Background(),        // ctx
    "book",                      // CollectionName
    "book_intro",                // fieldName
    idx,                         // entity.Index
    false,                       // async
)
if err != nil {
    log.Fatal("fail to create index:", err.Error())
}

milvusClient.createIndex(
        CreateIndexParam.newBuilder()
                .withCollectionName("book")
                .withFieldName("book_intro")
                .withIndexType(INDEX_TYPE)
                .withMetricType(MetricType.L2)
                .withExtraParam(INDEX_PARAM)
                .withSyncMode(Boolean.FALSE)
                .build());

# Follow the previous step.

Parameter	Description
`field_name`	Name of the vector field to build index on.
`index_params`	Parameters of the index to build.

Parameter	Description
`collection_name`	Name of the collection to build index in.
`field_name`	Name of the vector field to build index on.
`extra_params`	Parameters of the index to build.

Parameter	Description
`ctx`	Context to control API invocation process.
`CollectionName`	Name of the collection to build index on.
`fieldName`	Name of the vector field to build index on.
`entity.Index`	Parameters of the index to build.
`async`	Switch to control sync/async behavior. The deadline of context is not applied in sync building process.

What's next

Learn more basic operations of Milvus:
Explore API references for Milvus SDKs: