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?: string
apiVersion?: string

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

authOptions?: GoogleAuthOptions<JSONClient>
callerOptions?: AsyncCallerCallOptions
callerParams?: AsyncCallerParams
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.

GoogleVertexAILLMConnection.buildUrl

deployedIndexId?: string
docstore: Docstore
endpoint?: string

Hostname for the API call

index: string
indexEndpoint: string
location?: string

Region where the LLM is stored