Pular para o conteúdo principal

Class: VectorStoreIndex

The VectorStoreIndex, an index that stores the nodes only according to their vector embeddings.

Extends​

Constructors​

new VectorStoreIndex()​

private new VectorStoreIndex(init): VectorStoreIndex

Parameters​

• init: VectorIndexConstructorProps

Returns​

VectorStoreIndex

Overrides​

BaseIndex . constructor

Source​

packages/core/src/indices/vectorStore/index.ts:69

Properties​

docStore​

docStore: BaseDocumentStore

Inherited from​

BaseIndex . docStore

Source​

packages/core/src/indices/BaseIndex.ts:60

embedModel?​

optional embedModel: BaseEmbedding

Source​

packages/core/src/indices/vectorStore/index.ts:66

indexStore​

indexStore: BaseIndexStore

Overrides​

BaseIndex . indexStore

Source​

packages/core/src/indices/vectorStore/index.ts:65

indexStruct​

indexStruct: IndexDict

Inherited from​

BaseIndex . indexStruct

Source​

packages/core/src/indices/BaseIndex.ts:62

serviceContext?​

optional serviceContext: ServiceContext

Inherited from​

BaseIndex . serviceContext

Source​

packages/core/src/indices/BaseIndex.ts:58

storageContext​

storageContext: StorageContext

Inherited from​

BaseIndex . storageContext

Source​

packages/core/src/indices/BaseIndex.ts:59

vectorStores​

vectorStores: VectorStoreByType

Source​

packages/core/src/indices/vectorStore/index.ts:67

Methods​

asQueryEngine()​

asQueryEngine(options?): QueryEngine & RetrieverQueryEngine

Create a RetrieverQueryEngine. similarityTopK is only used if no existing retriever is provided.

Parameters​

• options?

• options.nodePostprocessors?: BaseNodePostprocessor[]

• options.preFilters?: MetadataFilters

• options.responseSynthesizer?: BaseSynthesizer

• options.retriever?: BaseRetriever

• options.similarityTopK?: number

Returns​

QueryEngine & RetrieverQueryEngine

Overrides​

BaseIndex . asQueryEngine

Source​

packages/core/src/indices/vectorStore/index.ts:283

asRetriever()​

asRetriever(options?): VectorIndexRetriever

Create a new retriever from the index.

Parameters​

• options?: Omit <VectorIndexRetrieverOptions, "index">

Returns​

VectorIndexRetriever

Overrides​

BaseIndex . asRetriever

Source​

packages/core/src/indices/vectorStore/index.ts:273

buildIndexFromNodes()​

buildIndexFromNodes(nodes, options?): Promise<void>

Get embeddings for nodes and place them into the index.

Parameters​

• nodes: BaseNode <Metadata>[]

• options?

• options.logProgress?: boolean

Returns​

Promise<void>

Source​

packages/core/src/indices/vectorStore/index.ts:186

deleteRefDoc()​

deleteRefDoc(refDocId, deleteFromDocStore): Promise<void>

Parameters​

• refDocId: string

• deleteFromDocStore: boolean= true

Returns​

Promise<void>

Overrides​

BaseIndex . deleteRefDoc

Source​

packages/core/src/indices/vectorStore/index.ts:345

deleteRefDocFromStore()​

protected deleteRefDocFromStore(vectorStore, refDocId): Promise<void>

Parameters​

• vectorStore: VectorStore

• refDocId: string

Returns​

Promise<void>

Source​

packages/core/src/indices/vectorStore/index.ts:357

getNodeEmbeddingResults()​

getNodeEmbeddingResults(nodes, options?): Promise <BaseNode <Metadata>[]>

Calculates the embeddings for the given nodes.

Parameters​

• nodes: BaseNode <Metadata>[]

An array of BaseNode objects representing the nodes for which embeddings are to be calculated.

• options?

An optional object containing additional parameters.

• options.logProgress?: boolean

A boolean indicating whether to log progress to the console (useful for debugging).

Returns​

Promise <BaseNode <Metadata>[]>

Source​

packages/core/src/indices/vectorStore/index.ts:163

insert()​

insert(document): Promise<void>

Insert a document into the index.

Parameters​

• document: Document <Metadata>

Returns​

Promise<void>

Inherited from​

BaseIndex . insert

Source​

packages/core/src/indices/BaseIndex.ts:92

insertNodes()​

insertNodes(nodes, options?): Promise<void>

Parameters​

• nodes: BaseNode <Metadata>[]

• options?

• options.logProgress?: boolean

Returns​

Promise<void>

Overrides​

BaseIndex . insertNodes

Source​

packages/core/src/indices/vectorStore/index.ts:329

insertNodesToStore()​

protected insertNodesToStore(newIds, nodes, vectorStore): Promise<void>

Parameters​

• newIds: string[]

• nodes: BaseNode <Metadata>[]

• vectorStore: VectorStore

Returns​

Promise<void>

Source​

packages/core/src/indices/vectorStore/index.ts:305

fromDocuments()​

static fromDocuments(documents, args): Promise <VectorStoreIndex>

High level API: split documents, get embeddings, and build index.

Parameters​

• documents: Document <Metadata>[]

• args: VectorIndexOptions & object= {}

Returns​

Promise <VectorStoreIndex>

Source​

packages/core/src/indices/vectorStore/index.ts:199

fromVectorStore()​

static fromVectorStore(vectorStore, serviceContext?): Promise <VectorStoreIndex>

Parameters​

• vectorStore: VectorStore

• serviceContext?: ServiceContext

Returns​

Promise <VectorStoreIndex>

Source​

packages/core/src/indices/vectorStore/index.ts:263

fromVectorStores()​

static fromVectorStores(vectorStores, serviceContext?): Promise <VectorStoreIndex>

Parameters​

• vectorStores: VectorStoreByType

• serviceContext?: ServiceContext

Returns​

Promise <VectorStoreIndex>

Source​

packages/core/src/indices/vectorStore/index.ts:240

init()​

static init(options): Promise <VectorStoreIndex>

The async init function creates a new VectorStoreIndex.

Parameters​

• options: VectorIndexOptions

Returns​

Promise <VectorStoreIndex>

Source​

packages/core/src/indices/vectorStore/index.ts:81

setupIndexStructFromStorage()​

static private setupIndexStructFromStorage(indexStore, options): Promise<undefined | IndexDict>

Parameters​

• indexStore: BaseIndexStore

• options: IndexStructOptions

Returns​

Promise<undefined | IndexDict>

Source​

packages/core/src/indices/vectorStore/index.ts:121