def llm_evaluate(sentences,sampled_passages):
    prompt = f"""You will be provided with a text passage 
                and your task is to rate the consistency of that text to 
                that of the provided context. Your answer must be only 
                a number between 0.0 and 1.0 rounded to the nearest two 
                decimal places where 0.0 represents no consistency and 
                1.0 represents perfect consistency and similarity. nn 
                Text passage: {sentences}. nn 
                Context: {sampled_passages[0]} nn 
                {sampled_passages[1]} nn 
                {sampled_passages[2]}."""

    completion = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": ""},
        {"role": "user", "content": prompt}
    ]
    )

    return completion.choices[0].message.content