Modellantwort mithilfe des ROUGE-Messwerts anhand einer Referenz (Ground Truth) bewerten

In diesem Codebeispiel wird gezeigt, wie Sie mit Vertex AI ROUGE-Messwerte zur Bewertung von Textzusammenfassungsmodellen berechnen. Es wird gezeigt, wie Sie eine Bewertungsaufgabe definieren und ROUGE-Werte für mehrere generierte Zusammenfassungen im Vergleich zu einer Referenzzusammenfassung berechnen.

Weitere Informationen

Eine ausführliche Dokumentation, die dieses Codebeispiel enthält, finden Sie hier:

• Gen AI Evaluation Service API

Codebeispiel

Go

Bevor Sie dieses Beispiel anwenden, folgen Sie den Go-Einrichtungsschritten in der Vertex AI-Kurzanleitung zur Verwendung von Clientbibliotheken. Weitere Informationen finden Sie in der Referenzdokumentation zur Vertex AI Go API.

Richten Sie zur Authentifizierung bei Vertex AI Standardanmeldedaten für Anwendungen ein. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.

import (
	"context"
	"fmt"
	"io"

	aiplatform "cloud.google.com/go/aiplatform/apiv1beta1"
	aiplatformpb "cloud.google.com/go/aiplatform/apiv1beta1/aiplatformpb"
	"google.golang.org/api/option"
)

// getROUGEScore evaluates a model response against a reference (ground truth) using the ROUGE metric
func getROUGEScore(w io.Writer, projectID, location string) error {
	// location = "us-central1"
	ctx := context.Background()
	apiEndpoint := fmt.Sprintf("%s-aiplatform.googleapis.com:443", location)
	client, err := aiplatform.NewEvaluationClient(ctx, option.WithEndpoint(apiEndpoint))

	if err != nil {
		return fmt.Errorf("unable to create aiplatform client: %w", err)
	}
	defer client.Close()

	modelResponse := `
The Great Barrier Reef, the world's largest coral reef system located in Australia,
is a vast and diverse ecosystem. However, it faces serious threats from climate change,
ocean acidification, and coral bleaching, endangering its rich marine life.
`
	reference := `
The Great Barrier Reef, the world's largest coral reef system, is
located off the coast of Queensland, Australia. It's a vast
ecosystem spanning over 2,300 kilometers with thousands of reefs
and islands. While it harbors an incredible diversity of marine
life, including endangered species, it faces serious threats from
climate change, ocean acidification, and coral bleaching.
`
	req := aiplatformpb.EvaluateInstancesRequest{
		Location: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		MetricInputs: &aiplatformpb.EvaluateInstancesRequest_RougeInput{
			RougeInput: &aiplatformpb.RougeInput{
				// Check the API reference for the list of supported ROUGE metric types:
				// https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#rougespec
				MetricSpec: &aiplatformpb.RougeSpec{
					RougeType: "rouge1",
				},
				Instances: []*aiplatformpb.RougeInstance{
					{
						Prediction: &modelResponse,
						Reference:  &reference,
					},
				},
			},
		},
	}

	resp, err := client.EvaluateInstances(ctx, &req)
	if err != nil {
		return fmt.Errorf("evaluateInstances failed: %v", err)
	}

	fmt.Fprintln(w, "evaluation results:")
	fmt.Fprintln(w, resp.GetRougeResults().GetRougeMetricValues())
	// Example response:
	// [score:0.6597938]

	return nil
}

Python

Bevor Sie dieses Beispiel anwenden, folgen Sie den Python-Einrichtungsschritten in der Vertex AI-Kurzanleitung zur Verwendung von Clientbibliotheken. Weitere Informationen finden Sie in der Referenzdokumentation zur Vertex AI Python API.

Richten Sie zur Authentifizierung bei Vertex AI Standardanmeldedaten für Anwendungen ein. Weitere Informationen finden Sie unter Authentifizierung für eine lokale Entwicklungsumgebung einrichten.

import pandas as pd

import vertexai
from vertexai.preview.evaluation import EvalTask

# TODO(developer): Update & uncomment line below
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

reference_summarization = """
The Great Barrier Reef, the world's largest coral reef system, is
located off the coast of Queensland, Australia. It's a vast
ecosystem spanning over 2,300 kilometers with thousands of reefs
and islands. While it harbors an incredible diversity of marine
life, including endangered species, it faces serious threats from
climate change, ocean acidification, and coral bleaching."""

# Compare pre-generated model responses against the reference (ground truth).
eval_dataset = pd.DataFrame(
    {
        "response": [
            """The Great Barrier Reef, the world's largest coral reef system located
        in Australia, is a vast and diverse ecosystem. However, it faces serious
        threats from climate change, ocean acidification, and coral bleaching,
        endangering its rich marine life.""",
            """The Great Barrier Reef, a vast coral reef system off the coast of
        Queensland, Australia, is the world's largest. It's a complex ecosystem
        supporting diverse marine life, including endangered species. However,
        climate change, ocean acidification, and coral bleaching are serious
        threats to its survival.""",
            """The Great Barrier Reef, the world's largest coral reef system off the
        coast of Australia, is a vast and diverse ecosystem with thousands of
        reefs and islands. It is home to a multitude of marine life, including
        endangered species, but faces serious threats from climate change, ocean
        acidification, and coral bleaching.""",
        ],
        "reference": [reference_summarization] * 3,
    }
)
eval_task = EvalTask(
    dataset=eval_dataset,
    metrics=[
        "rouge_1",
        "rouge_2",
        "rouge_l",
        "rouge_l_sum",
    ],
)
result = eval_task.evaluate()

print("Summary Metrics:\n")
for key, value in result.summary_metrics.items():
    print(f"{key}: \t{value}")

print("\n\nMetrics Table:\n")
print(result.metrics_table)
# Example response:
#
# Summary Metrics:
#
# row_count:      3
# rouge_1/mean:   0.7191161666666667
# rouge_1/std:    0.06765143922270488
# rouge_2/mean:   0.5441118566666666
# ...
# Metrics Table:
#
#                                        response                         reference  ...  rouge_l/score  rouge_l_sum/score
# 0  The Great Barrier Reef, the world's ...  \n    The Great Barrier Reef, the ...  ...       0.577320           0.639175
# 1  The Great Barrier Reef, a vast coral...  \n    The Great Barrier Reef, the ...  ...       0.552381           0.666667
# 2  The Great Barrier Reef, the world's ...  \n    The Great Barrier Reef, the ...  ...       0.774775           0.774775

Nächste Schritte

Informationen zum Suchen und Filtern von Codebeispielen für andere Google Cloud -Produkte finden Sie im Google Cloud Beispielbrowser.