Skip to main content

Interface: AzureAISearchOptions<T>

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​

• T extends R

Properties​

chunkFieldKey?​

optional chunkFieldKey: string

Index field storing the node text

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:118

compressionType?​

optional compressionType: KnownVectorSearchCompressionKind

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:108

credentials?​

optional credentials: DefaultAzureCredential | AzureKeyCredential

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:99

docIdFieldKey?​

optional docIdFieldKey: string

Index field storing doc_id

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:133

embeddingDimensionality?​

optional embeddingDimensionality: number

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:109

embeddingFieldKey?​

optional embeddingFieldKey: string

Index field storing the embedding vector

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:122

endpoint?​

optional endpoint: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:100

filterableMetadataFieldKeys?​

optional filterableMetadataFieldKeys: FilterableMetadataFieldKeysType

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:140

hiddenFieldKeys?​

optional hiddenFieldKeys: string[]

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.

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:139

idFieldKey?​

optional idFieldKey: string

Index field storing the id

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:114

indexClient?​

optional indexClient: SearchIndexClient

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:104

indexManagement?​

optional indexManagement: IndexManagement

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:105

indexMapping()?​

optional indexMapping: (enrichedDoc, metadata) => T

(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​

• enrichedDoc: BaseNode<Metadata>

The enriched document

• metadata: Record<string, unknown>

The metadata of the document

Returns​

T

The mapped index document

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:156

indexName?​

optional indexName: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:103

key?​

optional key: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:101

languageAnalyzer?​

optional languageAnalyzer: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:107

metadataStringFieldKey?​

optional metadataStringFieldKey: string

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

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:129

searchClient?​

optional searchClient: SearchClient<T>

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:106

serviceApiVersion?​

optional serviceApiVersion: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:102

userAgent?​

optional userAgent: string

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:98

vectorAlgorithmType?​

optional vectorAlgorithmType: KnownVectorSearchAlgorithmKind

Defined in​

packages/llamaindex/src/vector-store/azure/AzureAISearchVectorStore.ts:110