教學課程：使用 Python SDK 執行評估

本頁說明如何使用 Vertex AI SDK for Python 搭配 Gen AI Evaluation Service，執行模型評估。

事前準備

  1. 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.

    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.

    Go to project selector

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

  2. 安裝 Vertex AI SDK for Python 和 Gen AI Evaluation Service 依附元件：

    !pip install google-cloud-aiplatform[evaluation]

  3. 設定憑證。如果您是在 Colaboratory 中執行本快速入門，請執行以下操作：

    from google.colab import auth
auth.authenticate_user()

    如要瞭解其他環境，請參閱「向 Vertex AI 進行驗證」。

匯入程式庫

匯入程式庫，並設定專案和位置。

import pandas as pd

import vertexai
from vertexai.evaluation import EvalTask, PointwiseMetric, PointwiseMetricPromptTemplate
from google.cloud import aiplatform

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

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

請注意，EXPERIMENT_NAME 只能使用小寫英數字元和連字號，長度上限為 127 個半形字元。

根據條件設定評估指標

下列指標定義會根據兩個標準 (Fluency 和 Entertaining) 評估大型語言模型產生的文字品質。程式碼會使用這兩個條件定義名為 custom_text_quality 的指標：

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",
        },
    ),
)

準備資料集

新增下列程式碼，準備資料集：

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,
})

使用資料集執行評估

執行評估作業：

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

pointwise_result = eval_task.evaluate()

在 metrics_table Pandas DataFrame 中查看每個回應的評估結果：

pointwise_result.metrics_table

清除所用資源

如要避免系統向您的 Google Cloud 帳戶收取您在本頁所用資源的費用，請按照下列步驟操作。

刪除評估作業建立的 ExperimentRun：

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

後續步驟