运行评估

!pip install -q google-cloud-aiplatform[evaluation]

from vertexai.evaluation import (
    EvalTask,
    PairwiseMetric,
    PairwiseMetricPromptTemplate,
    PointwiseMetric,
    PointwiseMetricPromptTemplate,
    MetricPromptTemplateExamples，
)

eval_task = EvalTask(
    dataset=DATASET,
    metrics=[METRIC_1, METRIC_2, METRIC_3],
    experiment=EXPERIMENT_NAME,
)

eval_result = eval_task.evaluate(
    model=MODEL,
    prompt_template=PROMPT_TEMPLATE,
    experiment_run=EXPERIMENT_RUN,
)

# View all the available examples of model-based metrics
MetricPromptTemplateExamples.list_example_metric_names()

# Display the metric prompt template of a specific example metric
print(MetricPromptTemplateExamples.get_prompt_template('fluency'))

# Use the pre-defined model-based metrics directly
eval_task = EvalTask(
    dataset=EVAL_DATASET,
    metrics=[MetricPromptTemplateExamples.Pointwise.FLUENCY],
)

eval_result = eval_task.evaluate(
    model=MODEL,
)

# Define a pointwise metric with two custom criteria
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",
        },
        input_variables=["prompt"],
    ),
)

# Display the serialized metric prompt template
print(custom_text_quality.metric_prompt_template)

# Run evaluation using the custom_text_quality metric
eval_task = EvalTask(
    dataset=EVAL_DATASET,
    metrics=[custom_text_quality],
)
eval_result = eval_task.evaluate(
    model=MODEL,
)

# Define a pointwise multi-turn chat quality metric
pointwise_chat_quality_metric_prompt = """Evaluate the AI's contribution to a meaningful conversation, considering coherence, fluency, groundedness, and conciseness.
 Review the chat history for context. Rate the response on a 1-5 scale, with explanations for each criterion and its overall impact.

# Conversation History
{history}

# Current User Prompt
{prompt}

# AI-generated Response
{response}
"""

freeform_multi_turn_chat_quality_metric = PointwiseMetric(
    metric="multi_turn_chat_quality_metric",
    metric_prompt_template=pointwise_chat_quality_metric_prompt,
)

# Run evaluation using the freeform_multi_turn_chat_quality_metric metric
eval_task = EvalTask(
    dataset=EVAL_DATASET,
    metrics=[freeform_multi_turn_chat_quality_metric],
)
eval_result = eval_task.evaluate(
    model=MODEL,
)

#Prepare the dataset for evaluation.
sources = [
    "Dem Feuer konnte Einhalt geboten werden",
    "Schulen und Kindergärten wurden eröffnet.",
]

responses = [
    "The fire could be stopped",
    "Schools and kindergartens were open",
]

references = [
    "They were able to control the fire.",
    "Schools and kindergartens opened",
]

eval_dataset = pd.DataFrame({
    "source": sources,
    "response": responses,
    "reference": references,
})

# Set the metrics.

metrics = [
    "bleu",
    pointwise_metric.Comet(),
    pointwise_metric.MetricX(),
]

eval_task = evaluation.EvalTask(
    dataset=eval_dataset,
    metrics=metrics,
)
eval_result = eval_task.evaluate()

# Combine computation-based metrics "ROUGE" and "BLEU" with model-based metrics
eval_task = EvalTask(
    dataset=EVAL_DATASET,
    metrics=["rouge_l_sum", "bleu", custom_text_quality],
)
eval_result = eval_task.evaluate(
    model=MODEL,
)

from vertexai.evaluation import EvalTask

# GEMINI_RPM is the requests per minute (RPM) quota for gemini-1.5-pro in your region
# Evaluation Service QPS limit is equal to (gemini-1.5-pro RPM / 60 sec / default number of samples)
CUSTOM_EVAL_SERVICE_QPS_LIMIT = GEMINI_RPM / 60 / 4

eval_task = EvalTask(
    dataset=DATASET,
    metrics=[METRIC_1, METRIC_2, METRIC_3],
)

eval_result = eval_task.evaluate(
    evaluation_service_qps=CUSTOM_EVAL_SERVICE_QPS_LIMIT,
    # Specify a retry_timeout limit for a more responsive evaluation run
    # the default value is 600 (in seconds, or 10 minutes)
    retry_timeout=RETRY_TIMEOUT,
)