桂软guinsoft_rags

打包为 whl

安装打包工具（若未安装）

• pip install setuptools wheel

打包（生成dist目录，内含新whl文件）

• python setup.py bdist_wheel

验证

安装新包

• pip install dist/guinsoft_rags-1.0.3-py3-none-any.whl

验证功能（如导入包并执行测试代码）

• python -c "import guinsoft_rags; print(guinsoft_rags.version)"

快速开始

安装包

pip install -e .

评分

import httpx
from datasets import Dataset
from langchain_openai import ChatOpenAI
from guinsoft_ragas import evaluate
from guinsoft_ragas.llms.langchain import LangchainLLM
from guinsoft_ragas.metrics import AnswerCorrectnessGuinsoft

data_samples = {
    'question': ['When was the first super bowl?', 'Who won the most super bowls?'],
    'answer': [
        'The first superbowl was held on Jan 15, 1967',
        'The most super bowls have been won by The New England Patriots',
    ],
    'ground_truths': [
        ['The first superbowl was held on January 15, 1967.'],
        ['The New England Patriots have won the Super Bowl a record six times'],
    ],
}
_llm = ChatOpenAI(model="qwen3-max",
                  api_key="sk-xxxxx",
                  base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
                  temperature=temperature,
)
llm = LangchainLLM(_llm)
answer_correctness_guinsoft = AnswerCorrectnessGuinsoft(llm=llm)

dataset = Dataset.from_dict(data_samples)
score = evaluate(dataset, metrics=[answer_correctness_guinsoft])
print(score.to_pandas())