Interface MatchingEngineArgs

Parameters necessary to configure the Matching Engine.

interface MatchingEngineArgs {
    apiEndpoint?: string;
    apiVersion?: string;
    authOptions?: GoogleAuthOptions<JSONClient>;
    callerOptions?: AsyncCallerCallOptions;
    callerParams?: AsyncCallerParams;
    customModelURL?: string;
    deployedIndexId?: string;
    docstore: Docstore;
    endpoint?: string;
    index: string;
    indexEndpoint: string;
    location?: string;
}

Hierarchy

  • GoogleVertexAIConnectionParams<GoogleAuthOptions>
  • IndexEndpointConnectionParams
  • UpsertDatapointParams
    • MatchingEngineArgs

Implemented by

Properties

apiEndpoint? apiVersion? authOptions? callerOptions? callerParams? customModelURL? deployedIndexId? docstore endpoint? index indexEndpoint location?

Properties

OptionalapiEndpoint

apiEndpoint?: string

OptionalapiVersion

apiVersion?: string

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

OptionalauthOptions

authOptions?: GoogleAuthOptions<JSONClient>

OptionalcallerOptions

callerOptions?: AsyncCallerCallOptions

OptionalcallerParams

callerParams?: AsyncCallerParams

OptionalcustomModelURL

customModelURL?: string

If you are planning to connect to a model that lives under a custom endpoint provide the "customModelURL" which will override the automatic URL building

This is necessary in cases when you want to point to a fine-tuned model or a model that has been hidden under VertexAI Endpoints.

In those cases, specifying the GoogleVertexAIModelParams.model param will not be necessary and will be ignored.

See

GoogleVertexAILLMConnection.buildUrl

OptionaldeployedIndexId

deployedIndexId?: string

docstore

docstore: Docstore

Optionalendpoint

endpoint?: string

Hostname for the API call

index

index: string

indexEndpoint

indexEndpoint: string

Optionallocation

location?: string

Region where the LLM is stored

Settings

Member Visibility

On This Page

Properties