Zeno

%pip install zeno-client uptrain

ZENO_API_KEY = "sk-***************"
OPENAI_API_KEY = "zen_***************"

data = [
    {
      "question": "What causes diabetes?",
      "context": "Diabetes is a metabolic disorder characterized by high blood sugar levels. It is primarily caused by a combination of genetic and environmental factors, including obesity and lack of physical activity.",
      "response": "Diabetes is primarily caused by a combination of genetic and environmental factors, including obesity and lack of physical activity."
   },
   {
      "question": "What are the symptoms of a heart attack?",
      "context": "A heart attack, or myocardial infarction, occurs when the blood supply to the heart muscle is blocked. Symptoms of a heart attack may include chest pain or discomfort, shortness of breath, nausea, lightheadedness, and pain or discomfort in one or both arms, the jaw, neck, or back.",
      "response": "Symptoms of a heart attack may include chest pain or discomfort, shortness of breath, nausea, lightheadedness, and pain or discomfort in one or both arms, the jaw, neck, or back."
   },
   {
      "question": "Can stress cause physical health problems?",
      "context": "Stress is the body's response to challenges or threats. Yes, chronic stress can contribute to various physical health problems, including cardiovascular issues, digestive problems, and a weakened immune system.",
      "response": "Yes, chronic stress can contribute to various physical health problems, including cardiovascular issues, digestive problems, and a weakened immune system."
   },
   {
        'question': "What causes diabetes?",
        'context': "Diabetes is a metabolic disorder characterized by high blood sugar levels. It is primarily caused by a combination of genetic and environmental factors, including obesity and lack of physical activity.",
        'response': "Diabetes is caused by eating too much sugar, and reducing sugar intake can cure it completely."
    },
    {
        'question': "What are the symptoms of a heart attack?",
        'context': "A heart attack, or myocardial infarction, occurs when the blood supply to the heart muscle is blocked. Symptoms of a heart attack may include chest pain or discomfort, shortness of breath, nausea, lightheadedness, and pain or discomfort in one or both arms, the jaw, neck, or back.",
        'response': "Heart attack symptoms are usually just indigestion and can be relieved with antacids."
    },
    {
        'question': "Can stress cause physical health problems?",
        'context': "Stress is the body's response to challenges or threats. Yes, chronic stress can contribute to various physical health problems, including cardiovascular issues, digestive problems, and a weakened immune system.",
        'response': "Stress has no impact on physical health; it's just a mental state and doesn't affect the body."
    }
]

from uptrain import EvalLLM, Evals
import json
import pandas as pd

eval_llm = EvalLLM(openai_api_key = OPENAI_API_KEY)

res = eval_llm.evaluate(
    data = data,
    checks = [Evals.CONTEXT_RELEVANCE, Evals.RESPONSE_COMPLETENESS, Evals.FACTUAL_ACCURACY, Evals.RESPONSE_RELEVANCE]
)

df = pd.DataFrame(res)

from zeno_client import ZenoClient, ZenoMetric
client = ZenoClient(ZENO_API_KEY)

project = client.create_project(
    name="UpTrain Zeno Demo",
    description="Evaluation of LLMs using UpTrain",
    public=True,
    view={
        "data": {"type": "markdown"},
        "label": {"type": "text"},
        "output": {"type": "markdown"},
    },
    metrics=[
        ZenoMetric(name="context relevance", type="mean", columns=["score_context_relevance"]),
        ZenoMetric(name="response completeness", type="mean", columns=["score_response_completeness"]),
        ZenoMetric(name="factual accuracy", type="mean", columns=["score_factual_accuracy"]),
        ZenoMetric(name="response relevance", type="mean", columns=["score_response_relevance"]),
    ],
)

data_df = df[['question', 'context']]
data_df['id'] = data_df.index

project.upload_dataset(
    data_df, id_column="id", data_column="question", label_column="context"
)

output_df = df[
    [
        "score_context_relevance",
        "score_response_completeness",
        "score_factual_accuracy",
        "score_response_relevance",
    ]
].copy()

output_df["output"] = df[['response']]
output_df["id"] = output_df.index

project.upload_system(
    output_df, name="Demo", id_column="id", output_column="output"
)