Bereiten Sie das Bewertungs-Dataset vor.

prompts = [
    # Example 1
    (
        "Summarize the text in one sentence: As part of a comprehensive"
        " initiative to tackle urban congestion and foster sustainable urban"
        " living, a major city has revealed ambitious plans for an extensive"
        " overhaul of its public transportation system. The project aims not"
        " only to improve the efficiency and reliability of public transit but"
        " also to reduce the city's carbon footprint and promote eco-friendly"
        " commuting options. City officials anticipate that this strategic"
        " investment will enhance accessibility for residents and visitors"
        " alike, ushering in a new era of efficient, environmentally conscious"
        " urban transportation."
    ),
    # Example 2
    (
        "Summarize the text such that a five-year-old can understand: A team of"
        " archaeologists has unearthed ancient artifacts shedding light on a"
        " previously unknown civilization. The findings challenge existing"
        " historical narratives and provide valuable insights into human"
        " history."
    ),
]

responses = [
    # Example 1
    (
        "A major city is revamping its public transportation system to fight"
        " congestion, reduce emissions, and make getting around greener and"
        " easier."
    ),
    # Example 2
    (
        "Some people who dig for old things found some very special tools and"
        " objects that tell us about people who lived a long, long time ago!"
        " What they found is like a new puzzle piece that helps us understand"
        " how people used to live."
    ),
]

eval_dataset = pd.DataFrame({
    "prompt": prompts,
    "response": responses,
})

prompts = [
    # Example 1
    (
        "Based on the context provided, what is the hardest material? Context:"
        " Some might think that steel is the hardest material, or even"
        " titanium. However, diamond is actually the hardest material."
    ),
    # Example 2
    (
        "Based on the context provided, who directed The Godfather? Context:"
        " Mario Puzo and Francis Ford Coppola co-wrote the screenplay for The"
        " Godfather, and the latter directed it as well."
    ),
]

responses = [
    # Example 1
    "Diamond is the hardest material. It is harder than steel or titanium.",
    # Example 2
    "Francis Ford Coppola directed The Godfather.",
]

baseline_model_responses = [
    # Example 1
    "Steel is the hardest material.",
    # Example 2
    "John Smith.",
]

eval_dataset = pd.DataFrame(
  {
    "prompt":  prompts,
    "response":  responses,
    "baseline_model_response": baseline_model_responses,
  }
)

eval_dataset = pd.DataFrame({
  "response": ["The Roman Senate was filled with exuberance due to Pompey's defeat in Asia."],
  "reference": ["The Roman Senate was filled with exuberance due to successes against Catiline."],
})

json_responses = ["""{
    "content": "",
    "tool_calls":[{
      "name":"get_movie_info",
      "arguments": {"movie":"Mission Impossible", "time": "today 7:30PM"}
    }]
  }"""]

json_references = ["""{
    "content": "",
    "tool_calls":[{
      "name":"book_tickets",
      "arguments":{"movie":"Mission Impossible", "time": "today 7:30PM"}
      }]
  }"""]

eval_dataset = pd.DataFrame({
    "response": json_responses,
    "reference": json_references,
})