Halaman ini diterjemahkan oleh Cloud Translation API.

Panduan memulai: Alur kerja layanan evaluasi AI generatif

Halaman ini menunjukkan cara melakukan evaluasi berbasis model dengan layanan evaluasi AI Generatif menggunakan Vertex AI SDK untuk Python.

Sebelum memulai

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Make sure that billing is enabled for your Google Cloud project.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

Go to project selector

Make sure that billing is enabled for your Google Cloud project.
Instal Vertex AI SDK untuk Python dengan dependensi layanan evaluasi AI Generatif:
```
!pip install google-cloud-aiplatform[evaluation]
```
Siapkan kredensial Anda. Jika Anda menjalankan panduan memulai ini di Colaboratory, jalankan kode berikut:
```
from google.colab import auth
auth.authenticate_user()
```
Untuk lingkungan lain, lihat Melakukan Autentikasi ke Vertex AI.

Mengimpor library

Impor library dan siapkan project dan lokasi Anda.

import pandas as pd

import vertexai
from vertexai.evaluation import EvalTask, PointwiseMetric, PointwiseMetricPromptTemplate

PROJECT_ID = "PROJECT_ID"
LOCATION = "LOCATION"
EXPERIMENT_NAME = "EXPERIMENT_NAME"

vertexai.init(
    project=PROJECT_ID,
    location=LOCATION,
)

Perhatikan bahwa EXPERIMENT_NAME hanya dapat berisi karakter alfanumerik huruf kecil dan tanda hubung, hingga maksimal 127 karakter.

Menyiapkan metrik evaluasi berdasarkan kriteria Anda

Definisi metrik berikut mengevaluasi kualitas teks yang dihasilkan dari model bahasa besar berdasarkan dua kriteria: Fluency dan Entertaining. Kode menentukan metrik yang disebut custom_text_quality menggunakan dua kriteria tersebut:

custom_text_quality = PointwiseMetric(
    metric="custom_text_quality",
    metric_prompt_template=PointwiseMetricPromptTemplate(
        criteria={
            "fluency": (
                "Sentences flow smoothly and are easy to read, avoiding awkward"
                " phrasing or run-on sentences. Ideas and sentences connect"
                " logically, using transitions effectively where needed."
            ),
            "entertaining": (
                "Short, amusing text that incorporates emojis, exclamations and"
                " questions to convey quick and spontaneous communication and"
                " diversion."
            ),
        },
        rating_rubric={
            "1": "The response performs well on both criteria.",
            "0": "The response is somewhat aligned with both criteria",
            "-1": "The response falls short on both criteria",
        },
    ),
)

Menyiapkan set data

Tambahkan kode berikut untuk menyiapkan set data Anda:

responses = [
    # An example of good custom_text_quality
    "Life is a rollercoaster, full of ups and downs, but it's the thrill that keeps us coming back for more!",
    # An example of medium custom_text_quality
    "The weather is nice today, not too hot, not too cold.",
    # An example of poor custom_text_quality
    "The weather is, you know, whatever.",
]

eval_dataset = pd.DataFrame({
    "response" : responses,
})

Menjalankan evaluasi dengan set data Anda

Jalankan evaluasi:

eval_task = EvalTask(
    dataset=eval_dataset,
    metrics=[custom_text_quality],
    experiment=EXPERIMENT_NAME
)

pointwise_result = eval_task.evaluate()

Lihat hasil evaluasi untuk setiap respons di DataFrame Pandas metrics_table:

pointwise_result.metrics_table

Pembersihan

Agar tidak menimbulkan biaya pada akun Google Cloud Anda untuk resource yang digunakan pada halaman ini, ikuti langkah-langkah berikut.

Hapus ExperimentRun yang dibuat oleh evaluasi:

vertexai.ExperimentRun(
    run_name=pointwise_result.metadata["experiment_run"],
    experiment=pointwise_result.metadata["experiment"],
).delete()