Class MatchingEngine

A class that represents a connection to a Google Vertex AI Matching Engine instance.

Hierarchy

VectorStore
- MatchingEngine

Implements

MatchingEngineArgs

Constructors

constructor

new MatchingEngine(embeddings, args): MatchingEngine
Parameters
- embeddings: EmbeddingsInterface
- args: MatchingEngineArgs
Returns MatchingEngine
Overrides VectorStore.constructor
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:372

Properties

FilterType

FilterType: Restriction[]

apiEndpoint

apiEndpoint: string

The host to connect to for queries and upserts.

apiVersion

apiVersion: string = "v1"

The version of the API functions. Part of the path.

authOptions

authOptions: GoogleAuthOptions<JSONClient>

Explicitly set Google Auth credentials if you cannot get them from google auth application-default login This is useful for serverless or autoscaling environments like Fargate

caller

caller: AsyncCaller

callerOptions

callerOptions: AsyncCallerCallOptions

callerParams

callerParams: AsyncCallerParams

deployedIndexId

deployedIndexId: string

The id for the "deployed index", which is an identifier in the index endpoint that references the index (but is not the index id)

docstore

docstore: Docstore

Docstore that retains the document, stored by ID

embeddings

embeddings: EmbeddingsInterface

endpoint

endpoint: string = "us-central1-aiplatform.googleapis.com"

Hostname for the API call

index

index: string

The id for the index

indexEndpoint

indexEndpoint: string

The id for the index endpoint

indexEndpointClient

indexEndpointClient: IndexEndpointConnection

location

location: string = "us-central1"

Region where the LLM is stored

removeDatapointClient

removeDatapointClient: RemoveDatapointConnection

upsertDatapointClient

upsertDatapointClient: UpsertDatapointConnection

Methods

addDocuments

addDocuments(documents): Promise<void>
Parameters
- documents: Document<Record<string, any>>[]
Returns Promise<void>
Overrides VectorStore.addDocuments
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:433

addVectors

addVectors(vectors, documents): Promise<void>
Parameters
- vectors: number[][]
- documents: Document<Record<string, any>>[]
Returns Promise<void>
Overrides VectorStore.addVectors
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:439

asRetriever

asRetriever(kOrFields?, filter?, callbacks?, tags?, metadata?, verbose?): VectorStoreRetriever<MatchingEngine>
Parameters
- OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<MatchingEngine>>
- Optionalfilter: Restriction[]
- Optionalcallbacks: Callbacks
- Optionaltags: string[]
- Optionalmetadata: Record<string, unknown>
- Optionalverbose: boolean
Returns VectorStoreRetriever<MatchingEngine>
Inherited from VectorStore.asRetriever
- Defined in langchain-core/dist/vectorstores.d.ts:126

buildDatapoint

buildDatapoint(vector, document): IndexDatapoint
Create an index datapoint for the vector and document id. If an id does not exist, create it and set the document to its value.
Parameters
- vector: number[]
- document: IdDocument
Returns IndexDatapoint
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:574

cleanMetadata

cleanMetadata(documentMetadata): {
    [key: string]:
        | string
        | number
        | boolean
        | string[]
        | null;
}
Parameters
- documentMetadata: Record<string, any>
Returns {
    [key: string]:
        | string
        | number
        | boolean
        | string[]
        | null;
}
- [key: string]:
      | string
      | number
      | boolean
      | string[]
      | null
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:466

delete

delete(params): Promise<void>
Parameters
- params: MatchingEngineDeleteParams
Returns Promise<void>
Overrides VectorStore.delete
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:590

determinePublicAPIEndpoint

determinePublicAPIEndpoint(): Promise<PublicAPIEndpointInfo>
For this index endpoint, figure out what API Endpoint URL and deployed index ID should be used to do upserts and queries. Also sets the apiEndpoint and deployedIndexId property for future use.

Returns Promise<PublicAPIEndpointInfo>
The URL
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:677

getDeployedIndexId

getDeployedIndexId(): Promise<string>
Returns Promise<string>
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:718

getPublicAPIEndpoint

getPublicAPIEndpoint(): Promise<string>
Returns Promise<string>
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:712

`Optional`maxMarginalRelevanceSearch

maxMarginalRelevanceSearch(query, options, _callbacks): Promise<DocumentInterface<Record<string, any>>[]>
Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.
Parameters
- query: string
  Text to look up documents similar to.
- options: MaxMarginalRelevanceSearchOptions<Restriction[]>
- _callbacks: undefined | Callbacks
Returns Promise<DocumentInterface<Record<string, any>>[]>
- List of documents selected by maximal marginal relevance.
Inherited from VectorStore.maxMarginalRelevanceSearch
- Defined in langchain-core/dist/vectorstores.d.ts:123

metadataToRestrictions

metadataToRestrictions(documentMetadata): Restriction[]
Given the metadata from a document, convert it to an array of Restriction objects that may be passed to the Matching Engine and stored. The default implementation flattens any metadata and includes it as an "allowList". Subclasses can choose to convert some of these to "denyList" items or to add additional restrictions (for example, to format dates into a different structure or to add additional restrictions based on the date).
Parameters
- documentMetadata: Record<string, any>
  The metadata from a document
Returns Restriction[]
a Restriction[] (or an array of a subclass, from the FilterType)
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:530

similaritySearch

similaritySearch(query, k?, filter?, _callbacks?): Promise<DocumentInterface<Record<string, any>>[]>
Parameters
- query: string
- Optionalk: number
- Optionalfilter: Restriction[]
- Optional_callbacks: Callbacks
Returns Promise<DocumentInterface<Record<string, any>>[]>
Inherited from VectorStore.similaritySearch
- Defined in langchain-core/dist/vectorstores.d.ts:106

similaritySearchVectorWithScore

similaritySearchVectorWithScore(query, k, filter?): Promise<[Document<Record<string, any>>, number][]>
Parameters
- query: number[]
- k: number
- Optionalfilter: Restriction[]
Returns Promise<[Document<Record<string, any>>, number][]>
Overrides VectorStore.similaritySearchVectorWithScore
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:595

similaritySearchWithScore

similaritySearchWithScore(query, k?, filter?, _callbacks?): Promise<[DocumentInterface<Record<string, any>>, number][]>
Parameters
- query: string
- Optionalk: number
- Optionalfilter: Restriction[]
- Optional_callbacks: Callbacks
Returns Promise<[DocumentInterface<Record<string, any>>, number][]>
Inherited from VectorStore.similaritySearchWithScore
- Defined in langchain-core/dist/vectorstores.d.ts:107

toJSON

toJSON(): Serialized
Returns Serialized
Inherited from VectorStore.toJSON
- Defined in langchain-core/dist/load/serializable.d.ts:69

toJSONNotImplemented

toJSONNotImplemented(): SerializedNotImplemented
Returns SerializedNotImplemented
Inherited from VectorStore.toJSONNotImplemented
- Defined in langchain-core/dist/load/serializable.d.ts:70

`Static`fromDocuments

fromDocuments(docs, embeddings, dbConfig): Promise<VectorStore>
Parameters
- docs: Document<Record<string, any>>[]
- embeddings: EmbeddingsInterface
- dbConfig: MatchingEngineArgs
Returns Promise<VectorStore>
Overrides VectorStore.fromDocuments
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:740

`Static`fromTexts

fromTexts(texts, metadatas, embeddings, dbConfig): Promise<VectorStore>
Parameters
- texts: string[]
- metadatas: object | object[]
- embeddings: EmbeddingsInterface
- dbConfig: MatchingEngineArgs
Returns Promise<VectorStore>
Overrides VectorStore.fromTexts
- Defined in libs/langchain-community/src/vectorstores/googlevertexai.ts:725

Class MatchingEngine

Hierarchy

Implements

Index

Constructors

Properties

Methods

Constructors

constructor

Parameters

Returns MatchingEngine

Properties

FilterType

apiEndpoint

apiVersion

authOptions

caller

callerOptions

callerParams

deployedIndexId

docstore

embeddings

endpoint

index

indexEndpoint

indexEndpointClient

location

removeDatapointClient

upsertDatapointClient

Methods

addDocuments

Parameters

Returns Promise<void>

addVectors

Parameters

Returns Promise<void>

asRetriever

Parameters

Returns VectorStoreRetriever<MatchingEngine>

buildDatapoint

Parameters

Returns IndexDatapoint

cleanMetadata

Parameters

Returns { [key: string]: | string | number | boolean | string[] | null; }

[key: string]: | string | number | boolean | string[] | null

delete

Parameters

Returns Promise<void>

determinePublicAPIEndpoint

Returns Promise<PublicAPIEndpointInfo>

getDeployedIndexId

Returns Promise<string>

getPublicAPIEndpoint

Returns Promise<string>

OptionalmaxMarginalRelevanceSearch

Parameters

Returns Promise<DocumentInterface<Record<string, any>>[]>

metadataToRestrictions

Parameters

Returns Restriction[]

similaritySearch

Parameters

Returns Promise<DocumentInterface<Record<string, any>>[]>

similaritySearchVectorWithScore

Parameters

Returns Promise<[Document<Record<string, any>>, number][]>

similaritySearchWithScore

Parameters

Returns Promise<[DocumentInterface<Record<string, any>>, number][]>

toJSON

Returns Serialized

toJSONNotImplemented

Returns SerializedNotImplemented

StaticfromDocuments

Parameters

Returns Promise<VectorStore>

StaticfromTexts

Parameters

Returns Promise<VectorStore>

Returns {
[key: string]:
| string
| number
| boolean
| string[]
| null;
}

[key: string]:
| string
| number
| boolean
| string[]
| null

`Optional`maxMarginalRelevanceSearch

`Static`fromDocuments

`Static`fromTexts