Evaluate text generation models using Vertex AI Gen AI evaluation service

import (
	context_pkg "context"
	"fmt"
	"io"

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

// evaluateModelResponse evaluates the output of an LLM for groundedness, i.e., how well
// the model response connects with verifiable sources of information
func evaluateModelResponse(w io.Writer, projectID, location string) error {
	// location = "us-central1"
	ctx := context_pkg.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()

	// evaluate the pre-generated model response against the reference (ground truth)
	responseToEvaluate := `
The city is undertaking a major project to revamp its public transportation system.
This initiative is designed to improve efficiency, reduce carbon emissions, and promote
eco-friendly commuting. The city expects that this investment will enhance accessibility
and usher in a new era of sustainable urban transportation.
`
	reference := `
As part of a comprehensive initiative to tackle urban congestion and foster
sustainable urban living, a major city has revealed ambitious plans for an
extensive overhaul of its public transportation system. The project aims not
only to improve the efficiency and reliability of public transit but also to
reduce the city\'s carbon footprint and promote eco-friendly commuting options.
City officials anticipate that this strategic investment will enhance
accessibility for residents and visitors alike, ushering in a new era of
efficient, environmentally conscious urban transportation.
`
	req := aiplatformpb.EvaluateInstancesRequest{
		Location: fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		// Check the API reference for a full list of supported metric inputs:
		// https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#evaluateinstancesrequest
		MetricInputs: &aiplatformpb.EvaluateInstancesRequest_GroundednessInput{
			GroundednessInput: &aiplatformpb.GroundednessInput{
				MetricSpec: &aiplatformpb.GroundednessSpec{},
				Instance: &aiplatformpb.GroundednessInstance{
					Context:    &reference,
					Prediction: &responseToEvaluate,
				},
			},
		},
	}

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

	results := resp.GetGroundednessResult()
	fmt.Fprintf(w, "score: %.2f\n", results.GetScore())
	fmt.Fprintf(w, "confidence: %.2f\n", results.GetConfidence())
	fmt.Fprintf(w, "explanation:\n%s\n", results.GetExplanation())
	// Example response:
	// score: 1.00
	// confidence: 1.00
	// explanation:
	// STEP 1: All aspects of the response are found in the context.
	// The response accurately summarizes the city's plan to overhaul its public transportation system, highlighting the goals of ...
	// STEP 2: According to the rubric, the response is scored 1 because all aspects of the response are attributable to the context.

	return nil
}

import pandas as pd

import vertexai
from vertexai.preview.evaluation import EvalTask, MetricPromptTemplateExamples

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

eval_dataset = pd.DataFrame(
    {
        "instruction": [
            "Summarize the text in one sentence.",
            "Summarize the text such that a five-year-old can understand.",
        ],
        "context": [
            """As part of a comprehensive initiative to tackle urban congestion and foster
            sustainable urban living, a major city has revealed ambitious plans for an
            extensive overhaul of its public transportation system. The project aims not
            only to improve the efficiency and reliability of public transit but also to
            reduce the city\'s carbon footprint and promote eco-friendly commuting options.
            City officials anticipate that this strategic investment will enhance
            accessibility for residents and visitors alike, ushering in a new era of
            efficient, environmentally conscious urban transportation.""",
            """A team of archaeologists has unearthed ancient artifacts shedding light on a
            previously unknown civilization. The findings challenge existing historical
            narratives and provide valuable insights into human history.""",
        ],
        "response": [
            "A major city is revamping its public transportation system to fight congestion, reduce emissions, and make getting around greener and easier.",
            "Some people who dig for old things found some very special tools and objects that tell us about people who lived a long, long time ago! What they found is like a new puzzle piece that helps us understand how people used to live.",
        ],
    }
)

eval_task = EvalTask(
    dataset=eval_dataset,
    metrics=[
        MetricPromptTemplateExamples.Pointwise.SUMMARIZATION_QUALITY,
        MetricPromptTemplateExamples.Pointwise.GROUNDEDNESS,
        MetricPromptTemplateExamples.Pointwise.VERBOSITY,
        MetricPromptTemplateExamples.Pointwise.INSTRUCTION_FOLLOWING,
    ],
)

prompt_template = (
    "Instruction: {instruction}. Article: {context}. Summary: {response}"
)
result = eval_task.evaluate(prompt_template=prompt_template)

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:      2
# summarization_quality/mean:     3.5
# summarization_quality/std:      2.1213203435596424
# ...