GoogleApi.AIPlatform.V1.Model.GoogleCloudAiplatformV1Fact (google_api_ai_platform v0.27.0)

View Source

The fact used in grounding.

Attributes

  • query (type: String.t, default: nil) - Query that is used to retrieve this fact.
  • score (type: float(), default: nil) - If present, according to the underlying Vector DB and the selected metric type, the score can be either the distance or the similarity between the query and the fact and its range depends on the metric type. For example, if the metric type is COSINE_DISTANCE, it represents the distance between the query and the fact. The larger the distance, the less relevant the fact is to the query. The range is [0, 2], while 0 means the most relevant and 2 means the least relevant.
  • summary (type: String.t, default: nil) - If present, the summary/snippet of the fact.
  • title (type: String.t, default: nil) - If present, it refers to the title of this fact.
  • uri (type: String.t, default: nil) - If present, this uri links to the source of the fact.
  • vectorDistance (type: float(), default: nil) - If present, the distance between the query vector and this fact vector.

Summary

Functions

Unwrap a decoded JSON object into its complex fields.

Types

t()

@type t() :: %GoogleApi.AIPlatform.V1.Model.GoogleCloudAiplatformV1Fact{
  query: String.t() | nil,
  score: float() | nil,
  summary: String.t() | nil,
  title: String.t() | nil,
  uri: String.t() | nil,
  vectorDistance: float() | nil
}

Functions

decode(value, options)

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

Unwrap a decoded JSON object into its complex fields.