如何在 UI 中筛选实验

models = {
    "openai-gpt-4o": ChatOpenAI(model="gpt-4o", temperature=0),
    "openai-gpt-4o-mini": ChatOpenAI(model="gpt-4o-mini", temperature=0),
    "anthropic-claude-3-sonnet-20240229": ChatAnthropic(temperature=0, model_name="claude-3-sonnet-20240229")
}

prompts = {
    "singleminded": "always answer questions with the word banana.",
    "fruitminded": "always discuss fruit in your answers.",
    "basic": "you are a chatbot."
}

def answer_evaluator(run, example) -> dict:
    llm = ChatOpenAI(model="gpt-4o", temperature=0)
    answer_grader = hub.pull("langchain-ai/rag-answer-vs-reference") | llm
    score = answer_grader.invoke(
        {
            "question": example.inputs["question"],
            "correct_answer": example.outputs["answer"],
            "student_answer": run.outputs,
        }
    )
    return {"key": "correctness", "score": score["Score"]}

dataset_name = "Filterable Dataset"

for model_type, model in models.items():
    for prompt_type, prompt in prompts.items():
        def predict(example):
            return model.invoke(
                [("system", prompt), ("user", example["question"])]
            )

        model_provider = model_type.split("-")[0]
        model_name = model_type[len(model_provider) + 1:]

        evaluate(
            predict,
            data=dataset_name,
            evaluators=[answer_evaluator],
            # ADD IN METADATA HERE!!
            metadata={
                "model_provider": model_provider,
                "model_name": model_name,
                "prompt_id": prompt_type
            }
        )