Rubric-Based Evaluation ↗

from openai import AsyncOpenAI
from ragas.llms.base import llm_factory
from ragas.metrics.collections import DomainSpecificRubrics

# Setup
client = AsyncOpenAI()
llm = llm_factory("gpt-4o-mini", client=client)

# Reference-free evaluation (default)
metric = DomainSpecificRubrics(llm=llm)
result = await metric.ascore(
    user_input="What's the longest river in the world?",
    response="The longest river in the world is the Nile, stretching approximately 6,650 kilometers through northeastern Africa.",
)
print(f"Score: {result.value}, Feedback: {result.reason}")

# Reference-based evaluation
metric_with_ref = DomainSpecificRubrics(llm=llm, with_reference=True)
result = await metric_with_ref.ascore(
    user_input="What's the longest river in the world?",
    response="The longest river in the world is the Nile.",
    reference="The Nile is a major north-flowing river in northeastern Africa.",
)

from ragas.metrics.collections import DomainSpecificRubrics

my_custom_rubrics = {
    "score1_description": "Answer and ground truth are completely different",
    "score2_description": "Answer and ground truth are somewhat different",
    "score3_description": "Answer and ground truth are somewhat similar",
    "score4_description": "Answer and ground truth are similar",
    "score5_description": "Answer and ground truth are exactly the same",
}

metric = DomainSpecificRubrics(llm=llm, rubrics=my_custom_rubrics, with_reference=True)

result = await metric.ascore(
    user_input="What's the longest river in the world?",
    response="Based on the context, the Nile is the longest river.",
    retrieved_contexts=[
        "Scientists debate whether the Amazon or the Nile is the longest river.",
        "The Nile River was central to Ancient Egyptians' wealth and power.",
    ],
)

from ragas.metrics.collections import (
    RubricsScoreWithoutReference,
    RubricsScoreWithReference,
)

# Reference-free
metric_no_ref = RubricsScoreWithoutReference(llm=llm)

# Reference-based
metric_with_ref = RubricsScoreWithReference(llm=llm)

from openai import AsyncOpenAI
from ragas.llms.base import llm_factory
from ragas.metrics.collections import InstanceSpecificRubrics

# Setup
client = AsyncOpenAI()
llm = llm_factory("gpt-4o-mini", client=client)

metric = InstanceSpecificRubrics(llm=llm)

# Each sample can have its own rubrics
email_rubrics = {
    "score1_description": "The email is unprofessional or inappropriate",
    "score2_description": "The email lacks proper formatting or tone",
    "score3_description": "The email is acceptable but could be improved",
    "score4_description": "The email is professional with minor issues",
    "score5_description": "The email is highly professional and well-written",
}

result = await metric.ascore(
    user_input="Write a professional email declining a meeting invitation",
    response="Dear John, Thank you for the invitation...",
    rubrics=email_rubrics,
)
print(f"Score: {result.value}, Feedback: {result.reason}")

# Different rubrics for a different type of task
code_rubrics = {
    "score1_description": "The code doesn't work or has critical bugs",
    "score2_description": "The code has significant issues or is poorly structured",
    "score3_description": "The code works but lacks optimization or best practices",
    "score4_description": "The code is good with minor improvements possible",
    "score5_description": "The code is excellent, efficient, and follows best practices",
}

result = await metric.ascore(
    user_input="Write a function to sort a list",
    response="def sort_list(arr): return sorted(arr)",
    rubrics=code_rubrics,
)

result = await metric.ascore(
    user_input="Explain the water cycle",
    response="The water cycle involves evaporation, condensation, and precipitation.",
    reference="The water cycle describes how water evaporates from surfaces, rises into the atmosphere, condenses into clouds, and falls as precipitation.",
    retrieved_contexts=["Water cycle information from encyclopedia..."],
    rubrics={
        "score1_description": "Explanation is completely wrong",
        "score2_description": "Explanation has major inaccuracies",
        "score3_description": "Explanation is partially correct",
        "score4_description": "Explanation is mostly correct",
        "score5_description": "Explanation is comprehensive and accurate",
    },
)

from ragas import evaluate
from datasets import Dataset

from ragas.metrics import rubrics_score_without_reference, rubrics_score_with_reference

rows = {
    "question": [
        "What's the longest river in the world?",
    ],
    "ground_truth": [
        "The Nile is a major north-flowing river in northeastern Africa.",
    ],
    "answer": [
        "The longest river in the world is the Nile, stretching approximately 6,650 kilometers (4,130 miles) through northeastern Africa.",
    ],
    "contexts": [
        [
            "Scientists debate whether the Amazon or the Nile is the longest river in the world.",
            "The Nile River was central to the Ancient Egyptians' rise to wealth and power.",
        ],
    ]
}

dataset = Dataset.from_dict(rows)

result = evaluate(
    dataset,
    metrics=[
        rubrics_score_without_reference,
        rubrics_score_with_reference
    ],
)

from ragas.metrics._domain_specific_rubrics import RubricsScore

my_custom_rubrics = {
    "score1_description": "answer and ground truth are completely different",
    "score2_description": "answer and ground truth are somewhat different",
    "score3_description": "answer and ground truth are somewhat similar",
    "score4_description": "answer and ground truth are similar",
    "score5_description": "answer and ground truth are exactly the same",
}

rubrics_score = RubricsScore(rubrics=my_custom_rubrics)