Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window.

ConfidenceLevelMetrics

Evaluations metrics, at a specific confidence level.

JSON representation
{ "confidenceLevel": number, "metrics": { object (`Metrics`) } }

Fields

Fields
`confidenceLevel`	`number` The confidence level.
`metrics`	`object (Metrics)` The metrics at the specific confidence level.

confidenceLevel

number

The confidence level.

metrics

object (Metrics)

The metrics at the specific confidence level.

Metrics

Evaluation metrics, either in aggregate or about a specific entity.

JSON representation
{ "precision": number, "recall": number, "f1Score": number, "predictedOccurrencesCount": integer, "groundTruthOccurrencesCount": integer, "predictedDocumentCount": integer, "groundTruthDocumentCount": integer, "truePositivesCount": integer, "falsePositivesCount": integer, "falseNegativesCount": integer, "totalDocumentsCount": integer }

JSON representation

{
  "precision": number,
  "recall": number,
  "f1Score": number,
  "predictedOccurrencesCount": integer,
  "groundTruthOccurrencesCount": integer,
  "predictedDocumentCount": integer,
  "groundTruthDocumentCount": integer,
  "truePositivesCount": integer,
  "falsePositivesCount": integer,
  "falseNegativesCount": integer,
  "totalDocumentsCount": integer
}

Fields
`precision`	`number` The calculated precision.
`recall`	`number` The calculated recall.
`f1Score`	`number` The calculated f1 score.
`predictedOccurrencesCount`	`integer` The amount of occurrences in predicted documents.
`groundTruthOccurrencesCount`	`integer` The amount of occurrences in ground truth documents.
`predictedDocumentCount`	`integer` The amount of documents with a predicted occurrence.
`groundTruthDocumentCount`	`integer` The amount of documents with a ground truth occurrence.
`truePositivesCount`	`integer` The amount of true positives.
`falsePositivesCount`	`integer` The amount of false positives.
`falseNegativesCount`	`integer` The amount of false negatives.
`totalDocumentsCount`	`integer` The amount of documents that had an occurrence of this label.