Skip to main content

Class: AzureCosmosDBMongoDBVectorStore

Azure Cosmos DB for MongoDB vCore vector store. To use this, you should have both:

  • the mongodb NPM package installed
  • a connection string associated with a MongoDB VCore Cluster

You do not need to create a database or collection, it will be created automatically.

You also need an index on the collection, which is by default be created automatically using the createIndex method.

Extends​

Constructors​

new AzureCosmosDBMongoDBVectorStore()​

new AzureCosmosDBMongoDBVectorStore(init): AzureCosmosDBMongoDBVectorStore

Parameters​

• init: Partial<AzureCosmosDBMongoDBVectorStore> & object & VectorStoreBaseParams

Returns​

AzureCosmosDBMongoDBVectorStore

Overrides​

BaseVectorStore.constructor

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:91

Properties​

collectionName​

collectionName: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:66

dbName​

dbName: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:64

embeddingKey​

embeddingKey: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:77

embedModel​

embedModel: BaseEmbedding

Inherited from​

BaseVectorStore.embedModel

Defined in​

packages/llamaindex/src/vector-store/types.ts:92

flatMetadata​

flatMetadata: boolean = true

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:62

idKey​

idKey: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:79

indexedMetadataFields​

indexedMetadataFields: string[]

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:68

indexName​

indexName: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:75

indexOptions​

indexOptions: AzureCosmosDBMongoDBIndexOptions

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:85

isEmbeddingQuery?​

optional isEmbeddingQuery: boolean

Inherited from​

BaseVectorStore.isEmbeddingQuery

Defined in​

packages/llamaindex/src/vector-store/types.ts:94

metadataKey​

metadataKey: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:83

mongodbClient​

mongodbClient: MongoClient

The used MongoClient. If not given, a new MongoClient is created based on the MONGODB_URI env variable.

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:73

storesText​

storesText: boolean = true

Overrides​

BaseVectorStore.storesText

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:61

textKey​

textKey: string

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:81

Methods​

add()​

add(nodes): Promise<string[]>

Parameters​

• nodes: BaseNode<Metadata>[]

Returns​

Promise<string[]>

Overrides​

BaseVectorStore.add

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:139

checkIndexExists()​

checkIndexExists(): Promise<boolean>

Checks if the specified index name during instance construction exists on the collection.

Returns​

Promise<boolean>

A promise that resolves to a boolean indicating if the index exists.

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:310

client()​

client(): MongoClient

Returns​

MongoClient

Overrides​

BaseVectorStore.client

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:123

createIndex()​

createIndex(dimensions, indexType, similarity): Promise<void>

Creates an index on the collection with the specified index name during instance construction.

Setting the numLists parameter correctly is important for achieving good accuracy and performance. Since the vector store uses IVF as the indexing strategy, you should create the index only after you have loaded a large enough sample documents to ensure that the centroids for the respective buckets are faily distributed.

Parameters​

• dimensions: undefined | number = undefined

Number of dimensions for vector similarity. The maximum number of supported dimensions is 2000. If no number is provided, it will be determined automatically by embedding a short text.

• indexType: "hnsw" | "ivf" | "diskann" = "ivf"

Index Type for Mongo vCore index.

• similarity: AzureCosmosDBMongoDBSimilarityType = AzureCosmosDBMongoDBSimilarityType.COS

Similarity metric to use with the IVF index. Possible options are:

  • CosmosDBSimilarityType.COS (cosine distance)
  • CosmosDBSimilarityType.L2 (Euclidean distance)
  • CosmosDBSimilarityType.IP (inner product)

Returns​

Promise<void>

A promise that resolves when the index has been created.

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:257

delete()​

delete(id, deleteOptions?): Promise<void>

Removes specified documents from the AzureCosmosDBMongoDBVectorStore.

Parameters​

• id: string

• deleteOptions?: object

Returns​

Promise<void>

A promise that resolves when the documents have been removed.

Overrides​

BaseVectorStore.delete

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:177

deleteIndex()​

deleteIndex(indexName): Promise<void>

Deletes the index specified during instance construction if it exists.

Parameters​

• indexName: string

Returns​

Promise<void>

A promise that resolves when the index has been deleted.

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:320

ensureCollection()​

ensureCollection(): Promise<Collection<Document>>

Returns​

Promise<Collection<Document>>

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:127

query()​

query(query, options?): Promise<VectorStoreQueryResult>

Parameters​

• query: VectorStoreQuery

• options?: object

Returns​

Promise<VectorStoreQueryResult>

Overrides​

BaseVectorStore.query

Defined in​

packages/llamaindex/src/vector-store/AzureCosmosDBMongoVectorStore.ts:187