View Source GoogleApi.Dialogflow.V3.Model.GoogleCloudDialogflowCxV3GenerativeSettingsKnowledgeConnectorSettings (google_api_dialogflow v0.78.0)

Settings for knowledge connector. These parameters are used for LLM prompt like "You are . You are a helpful and verbose at , . Your task is to help humans on ".

Attributes

agent (type: String.t, default: nil) - Name of the virtual agent. Used for LLM prompt. Can be left empty.
agentIdentity (type: String.t, default: nil) - Identity of the agent, e.g. "virtual agent", "AI assistant".
agentScope (type: String.t, default: nil) - Agent scope, e.g. "Example company website", "internal Example company website for employees", "manual of car owner".
business (type: String.t, default: nil) - Name of the company, organization or other entity that the agent represents. Used for knowledge connector LLM prompt and for knowledge search.
businessDescription (type: String.t, default: nil) - Company description, used for LLM prompt, e.g. "a family company selling freshly roasted coffee beans".
disableDataStoreFallback (type: boolean(), default: nil) - Whether to disable fallback to Data Store search results (in case the LLM couldn't pick a proper answer). Per default the feature is enabled.

Summary

Types

t()

Functions

decode(value, options)

Unwrap a decoded JSON object into its complex fields.

Types

t()

@type t() ::
  %GoogleApi.Dialogflow.V3.Model.GoogleCloudDialogflowCxV3GenerativeSettingsKnowledgeConnectorSettings{
    agent: String.t() | nil,
    agentIdentity: String.t() | nil,
    agentScope: String.t() | nil,
    business: String.t() | nil,
    businessDescription: String.t() | nil,
    disableDataStoreFallback: boolean() | nil
  }

Functions

decode(value, options)

@spec decode(struct(), keyword()) :: struct()

Unwrap a decoded JSON object into its complex fields.