VectorStoreIndex

Defined in: llamaindex/src/indices/vectorStore/index.ts:73

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

Extends

• BaseIndex<IndexDict>

Properties

storageContext

storageContext: StorageContext

Defined in: llamaindex/src/indices/BaseIndex.ts:27

Inherited from

BaseIndex.storageContext

---

docStore

docStore: BaseDocumentStore

Defined in: llamaindex/src/indices/BaseIndex.ts:28

Inherited from

BaseIndex.docStore

---

indexStruct

indexStruct: IndexDict

Defined in: llamaindex/src/indices/BaseIndex.ts:30

Inherited from

BaseIndex.indexStruct

---

indexStore

indexStore: BaseIndexStore

Defined in: llamaindex/src/indices/vectorStore/index.ts:74

Overrides

BaseIndex.indexStore

---

embedModel?

optional embedModel: BaseEmbedding

Defined in: llamaindex/src/indices/vectorStore/index.ts:75

---

vectorStores

vectorStores: VectorStoreByType

Defined in: llamaindex/src/indices/vectorStore/index.ts:76

Methods

insert()

insert(document): Promise<void>

Defined in: llamaindex/src/indices/BaseIndex.ts:68

Insert a document into the index.

Parameters

document

Document<Metadata>

Returns

Promise<void>

Inherited from

BaseIndex.insert

---

init()

static init(options): Promise<VectorStoreIndex>

Defined in: llamaindex/src/indices/vectorStore/index.ts:90

The async init function creates a new VectorStoreIndex.

Parameters

options

VectorIndexOptions

Returns

Promise<VectorStoreIndex>

---

getNodeEmbeddingResults()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:170

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.

logProgress?

boolean

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

Returns

Promise<BaseNode<Metadata>[]>

---

buildIndexFromNodes()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:193

Get embeddings for nodes and place them into the index.

Parameters

nodes

BaseNode<Metadata>[]

options?

logProgress?

boolean

Returns

Promise<void>

---

fromDocuments()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:206

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

Parameters

documents

Document<Metadata>[]

args

VectorIndexOptions & object = {}

Returns

Promise<VectorStoreIndex>

---

fromVectorStores()

static fromVectorStores(vectorStores): Promise<VectorStoreIndex>

Defined in: llamaindex/src/indices/vectorStore/index.ts:251

Parameters

vectorStores

VectorStoreByType

Returns

Promise<VectorStoreIndex>

---

fromVectorStore()

static fromVectorStore(vectorStore): Promise<VectorStoreIndex>

Defined in: llamaindex/src/indices/vectorStore/index.ts:270

Parameters

vectorStore

BaseVectorStore<unknown>

Returns

Promise<VectorStoreIndex>

---

asRetriever()

asRetriever(options?): VectorIndexRetriever

Defined in: llamaindex/src/indices/vectorStore/index.ts:274

Create a new retriever from the index.

Parameters

options?

Omit<object & object, "index"> | Omit<object & object, "index">

Returns

VectorIndexRetriever

Overrides

BaseIndex.asRetriever

---

asQueryEngine()

asQueryEngine(options?): RetrieverQueryEngine

Defined in: llamaindex/src/indices/vectorStore/index.ts:284

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

Parameters

options?

retriever?

BaseRetriever

responseSynthesizer?

BaseSynthesizer

preFilters?

MetadataFilters

nodePostprocessors?

BaseNodePostprocessor[]

similarityTopK?

number

Returns

RetrieverQueryEngine

Overrides

BaseIndex.asQueryEngine

---

asChatEngine()

asChatEngine(options): ContextChatEngine

Defined in: llamaindex/src/indices/vectorStore/index.ts:310

Convert the index to a chat engine.

Parameters

options

VectorIndexChatEngineOptions = {}

The options for creating the chat engine

Returns

ContextChatEngine

A ContextChatEngine that uses the index's retriever to get context for each query

Overrides

BaseIndex.asChatEngine

---

insertNodesToStore()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:324

Parameters

newIds

string[]

nodes

BaseNode<Metadata>[]

vectorStore

BaseVectorStore<unknown>

Returns

Promise<void>

---

insertNodes()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:348

Parameters

nodes

BaseNode<Metadata>[]

options?

logProgress?

boolean

Returns

Promise<void>

Overrides

BaseIndex.insertNodes

---

deleteRefDoc()

deleteRefDoc(refDocId, deleteFromDocStore): Promise<void>

Defined in: llamaindex/src/indices/vectorStore/index.ts:364

Parameters

refDocId

string

deleteFromDocStore

boolean = true

Returns

Promise<void>

Overrides

BaseIndex.deleteRefDoc

---

deleteRefDocFromStore()

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

Defined in: llamaindex/src/indices/vectorStore/index.ts:376

Parameters

vectorStore

BaseVectorStore<unknown>

refDocId

string

Returns

Promise<void>