Skip to content
vectorstores Documentation

AzureAISearchVectorStore

Defined in: packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:282

Azure AI Search vector store.

Example

Section titled “Example”
import { DefaultAzureCredential, getBearerTokenProvider} from "@azure/identity";
import {KnownAnalyzerNames, KnownVectorSearchAlgorithmKind } from "@azure/search-documents";


// 1- Setup Azure OpenAI
const azureADTokenProvider = getBearerTokenProvider(
 new DefaultAzureCredential(),
 "https://cognitiveservices.azure.com/.default",
);


// IMPORTANT: You need to deploy your own embedding model as well as your own chat completion model
// NOTE: You can use whatever embedding model and language model that is supported by vectorstores
const azure = {
 azureADTokenProvider,
 deployment: process.env.AZURE_DEPLOYMENT_NAME,
};
Settings.llm = new OpenAI({ azure });
Settings.embedModel = new OpenAIEmbedding({
 model: process.env.EMBEDDING_MODEL,
 azure: {
   ...azure,
   deployment: process.env.EMBEDDING_MODEL,
 },
});


// ---------------------------------------------------------
// 2- Setup Azure AI Search
// Define env variables in .env file
// AZURE_AI_SEARCH_ENDPOINT=
// AZURE_AI_SEARCH_KEY=
// AZURE_OPENAI_ENDPOINT=
// EMBEDDING_MODEL=text-embedding-ada-002
// AZURE_DEPLOYMENT_NAME=gpt-4
// AZURE_API_VERSION=2024-09-01-preview


// Define index name
const indexName = "vectorstores-vector-store";


// ---------------------------------------------------------
// 3a- Create Index (if it does not exist)
// id:        Edm.String
// chunk:      Edm.String
// embedding:  Collection(Edm.Single)
// metadata:  Edm.String
// doc_id:    Edm.String
// author:    Edm.String
// theme:      Edm.String
// director:  Edm.String


// Define metadata fields with their respective configurations
const metadataFields = {
 author: "author",
 theme: ["theme", MetadataIndexFieldType.STRING],
 director: "director",
};


// Define index parameters and vector store configuration
// Index validation:
// - IndexManagement.VALIDATE_INDEX: will validate before creating emnbedding index and will throw a runtime error if the index does not exist
// - IndexManagement.NO_VALIDATION: will try to access the index and will throw a runtime error if the index does not exist
// - IndexManagement.CREATE_IF_NOT_EXISTS: will create the index if it does not exist


const vectorStore = new AzureAISearchVectorStore({
 filterableMetadataFieldKeys:
   metadataFields as unknown as FilterableMetadataFieldKeysType,
 indexName,
 indexManagement: IndexManagement.CREATE_IF_NOT_EXISTS,
 idFieldKey: "id",
 chunkFieldKey: "chunk",
 embeddingFieldKey: "embedding",
 metadataStringFieldKey: "metadata",
 docIdFieldKey: "doc_id",
 embeddingDimensionality: 1536,
 hiddenFieldKeys: ["embedding"],
 languageAnalyzer: KnownAnalyzerNames.EnLucene,
 // store vectors on disk
 vectorAlgorithmType: KnownVectorSearchAlgorithmKind.ExhaustiveKnn,


 // Optional: Set to "scalar" or "binary" if using HNSW
 compressionType: KnownVectorSearchCompressionKind.BinaryQuantization,
});


// ---------------------------------------------------------
// 3a- Loading documents
// Load the documents stored in the data/paul_graham/ using the SimpleDirectoryReader
// NOTE: You can use whatever reader that is supported by vectorstores


// Load documents using a directory reader
const documents = await new SimpleDirectoryReader().loadData(
 "data/paul_graham/",
);


// Create index from documents with the specified vector store
const index = await VectorStoreIndex.fromDocuments(documents, {
 vectorStore,
 docStoreStrategy: DocStoreStrategy.UPSERTS,
});


const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
 query: "What did the author do growing up?",
 similarityTopK: 3,
} as any);
console.log({ response });


## Extends


- [`BaseVectorStore`](basevectorstore.md)


## Type Parameters


### T


`T` *extends* [`R`](../type-aliases/r.md)


## Constructors


### Constructor


> **new AzureAISearchVectorStore**\<`T`\>(`options`): `AzureAISearchVectorStore`\<`T`\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:309](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L309)


#### Parameters


##### options


[`AzureAISearchOptions`](../interfaces/azureaisearchoptions.md)\<`T`\> & [`VectorStoreBaseParams`](../type-aliases/vectorstorebaseparams.md)


#### Returns


`AzureAISearchVectorStore`\<`T`\>


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`constructor`](basevectorstore.md#constructor)


## Properties


### storesText


> **storesText**: `boolean` = `true`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:283](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L283)


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`storesText`](basevectorstore.md#storestext)


***


### \_searchClient


> **\_searchClient**: `SearchClient`\<`T`\> \| `undefined`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:284](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L284)


***


### \_indexClient


> **\_indexClient**: `SearchIndexClient` \| `undefined`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:290](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L290)


***


### flatMetadata


> **flatMetadata**: `boolean` = `true`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:296](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L296)


***


### embedModel


> **embedModel**: [`BaseEmbedding`](baseembedding.md)


Defined in: [packages/core/src/vector-store/index.ts:128](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/core/src/vector-store/index.ts#L128)


#### Inherited from


[`BaseVectorStore`](basevectorstore.md).[`embedModel`](basevectorstore.md#embedmodel)


***


### isEmbeddingQuery?


> `optional` **isEmbeddingQuery**: `boolean`


Defined in: [packages/core/src/vector-store/index.ts:130](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/core/src/vector-store/index.ts#L130)


#### Inherited from


[`BaseVectorStore`](basevectorstore.md).[`isEmbeddingQuery`](basevectorstore.md#isembeddingquery)


## Methods


### createSearchIndexClient()


> **createSearchIndexClient**(`options`): `void`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:858](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L858)


#### Parameters


##### options


[`AzureAISearchOptions`](../interfaces/azureaisearchoptions.md)\<`T`\>


#### Returns


`void`


***


### createSearchClient()


> **createSearchClient**(`options`): `void`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:875](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L875)


#### Parameters


##### options


[`AzureAISearchOptions`](../interfaces/azureaisearchoptions.md)\<`T`\>


#### Returns


`void`


***


### client()


> **client**(): `SearchClient`\<`T`\> \| `undefined`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1059](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1059)


Get search client


#### Returns


`SearchClient`\<`T`\> \| `undefined`


Azure AI Search client. See SearchClient


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`client`](basevectorstore.md#client-1)


***


### indexClient()


> **indexClient**(): `SearchIndexClient` \| `undefined`


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1067](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1067)


Get index client


#### Returns


`SearchIndexClient` \| `undefined`


Azure AI Search index client. See SearchIndexClient


***


### add()


> **add**(`nodes`): `Promise`\<`string`[]\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1076](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1076)


Add nodes to index associated with the configured search client.


#### Parameters


##### nodes


[`BaseNode`](basenode.md)\<[`Metadata`](../type-aliases/metadata.md)\>[]


List of nodes with embeddings to add to the index


#### Returns


`Promise`\<`string`[]\>


List of node IDs that were added to the index


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`add`](basevectorstore.md#add)


***


### delete()


> **delete**(`refDocId`): `Promise`\<`void`\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1141](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1141)


Delete documents from the AI Search Index with docIdFieldKey (doc_id) field equal to refDocId.


#### Parameters


##### refDocId


`string`


The reference document ID to delete from the index


#### Returns


`Promise`\<`void`\>


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`delete`](basevectorstore.md#delete)


***


### getNodes()


> **getNodes**(`nodeIds?`, `filters?`, `limit?`): `Promise`\<[`BaseNode`](basenode.md)\<[`Metadata`](../type-aliases/metadata.md)\>[]\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1188](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1188)


Get nodes asynchronously from the Azure AI Search index.


#### Parameters


##### nodeIds?


`string`[]


List of node IDs to retrieve from the index


##### filters?


[`MetadataFilters`](../interfaces/metadatafilters.md)


Metadata filters to apply to the search


##### limit?


`number`


Maximum number of nodes to retrieve


#### Returns


`Promise`\<[`BaseNode`](basenode.md)\<[`Metadata`](../type-aliases/metadata.md)\>[]\>


List of nodes retrieved from the index


***


### query()


> **query**(`query`): `Promise`\<[`VectorStoreQueryResult`](../interfaces/vectorstorequeryresult.md)\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1241](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1241)


#### Parameters


##### query


[`VectorStoreQuery`](../interfaces/vectorstorequery.md)\<`unknown`\> & `object`


#### Returns


`Promise`\<[`VectorStoreQueryResult`](../interfaces/vectorstorequeryresult.md)\>


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`query`](basevectorstore.md#query)


***


### exists()


> **exists**(`refDocId`): `Promise`\<`boolean`\>


Defined in: [packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts:1298](https://github.com/marcusschiesser/vectorstores/blob/ddf6b48881a800a24be35adebce6878566cf0014/packages/providers/storage/azure/src/vectorStore/AzureAISearchVectorStore.ts#L1298)


Check if any nodes exist for the given document reference ID.
Used for de-duplication during ingestion.


#### Parameters


##### refDocId


`string`


The reference document ID to check


#### Returns


`Promise`\<`boolean`\>


true if any nodes with this ref_doc_id exist


#### Overrides


[`BaseVectorStore`](basevectorstore.md).[`exists`](basevectorstore.md#exists)