Skip to content
vectorstores Documentation

AzureAISearchOptions

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:100

Embeddings and documents are stored in an Azure AI Search index, a merge or upload approach is used when adding embeddings. When adding multiple embeddings the index is updated by this vector store in batches of 10 documents, very large nodes may result in failure due to the batch byte size being exceeded.

Type Parameters

Section titled “Type Parameters”

T

Section titled “T”

T extends R

Properties

Section titled “Properties”

userAgent?

Section titled “userAgent?”

optional userAgent: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:101

credential?

Section titled “credential?”

optional credential: DefaultAzureCredential | AzureKeyCredential | ManagedIdentityCredential

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:102

endpoint?

Section titled “endpoint?”

optional endpoint: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:106

key?

Section titled “key?”

optional key: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:107

serviceApiVersion?

Section titled “serviceApiVersion?”

optional serviceApiVersion: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:108

indexName?

Section titled “indexName?”

optional indexName: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:109

indexClient?

Section titled “indexClient?”

optional indexClient: SearchIndexClient

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:110

indexManagement?

Section titled “indexManagement?”

optional indexManagement: IndexManagement

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:111

searchClient?

Section titled “searchClient?”

optional searchClient: SearchClient<T>

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:112

languageAnalyzer?

Section titled “languageAnalyzer?”

optional languageAnalyzer: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:113

compressionType?

Section titled “compressionType?”

optional compressionType: KnownVectorSearchCompressionKind

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:114

embeddingDimensionality?

Section titled “embeddingDimensionality?”

optional embeddingDimensionality: number

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:115

vectorAlgorithmType?

Section titled “vectorAlgorithmType?”

optional vectorAlgorithmType: KnownVectorSearchAlgorithmKind

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:116

idFieldKey?

Section titled “idFieldKey?”

optional idFieldKey: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:120

Index field storing the id

chunkFieldKey?

Section titled “chunkFieldKey?”

optional chunkFieldKey: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:124

Index field storing the node text

embeddingFieldKey?

Section titled “embeddingFieldKey?”

optional embeddingFieldKey: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:128

Index field storing the embedding vector

metadataStringFieldKey?

Section titled “metadataStringFieldKey?”

optional metadataStringFieldKey: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:135

Index field storing node metadata as a json string. Schema is arbitrary, to filter on metadata values they must be stored as separate fields in the index, use filterable_metadata_field_keys to specify the metadata values that should be stored in these filterable fields

docIdFieldKey?

Section titled “docIdFieldKey?”

optional docIdFieldKey: string

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:139

Index field storing doc_id

hiddenFieldKeys?

Section titled “hiddenFieldKeys?”

optional hiddenFieldKeys: string[]

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:145

List of index fields that should be hidden from the client. This is useful for fields that are not needed for retrieving, but are used for similarity search, like the embedding field.

filterableMetadataFieldKeys?

Section titled “filterableMetadataFieldKeys?”

optional filterableMetadataFieldKeys: FilterableMetadataFieldKeysType

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:146

indexMapping()?

Section titled “indexMapping()?”

optional indexMapping: (enrichedDoc, metadata) => T

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:162

(Optional) function used to map document fields to the AI search index fields If none is specified a default mapping is provided which uses the field keys. The keys in the enriched document are: ["id", "chunk", "embedding", "metadata"].

The default mapping is:

  • "id" to idFieldKey
  • "chunk" to chunkFieldKey
  • "embedding" to embeddingFieldKey
  • "metadata" to metadataFieldKey

Parameters

Section titled “Parameters”
enrichedDoc
Section titled “enrichedDoc”

BaseNode

The enriched document

metadata
Section titled “metadata”

Record<string, unknown>

The metadata of the document

Returns

Section titled “Returns”

T

The mapped index document