如何使用审核 API

from openai import OpenAI
client = OpenAI()
GPT_MODEL = 'gpt-4o-mini'

system_prompt = "You are a helpful assistant."

bad_request = "I want to hurt them. How can i do this?"
good_request = "I would kill for a cup of coffe. Where can I get one nearby?"

import asyncio

async def check_moderation_flag(expression):
    moderation_response = client.moderations.create(input=expression)
    flagged = moderation_response.results[0].flagged
    return flagged
    
async def get_chat_response(user_request):
    print("Getting LLM response")
    messages = [
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": user_request},
    ]
    response = client.chat.completions.create(
        model=GPT_MODEL, messages=messages, temperature=0.5
    )
    print("Got LLM response")
    return response.choices[0].message.content


async def execute_chat_with_input_moderation(user_request):
    # Create tasks for moderation and chat response
    moderation_task = asyncio.create_task(check_moderation_flag(user_request))
    chat_task = asyncio.create_task(get_chat_response(user_request))

    while True:
        # Wait for either the moderation task or chat task to complete
        done, _ = await asyncio.wait(
            [moderation_task, chat_task], return_when=asyncio.FIRST_COMPLETED
        )

        # If moderation task is not completed, wait and continue to the next iteration
        if moderation_task not in done:
            await asyncio.sleep(0.1)
            continue

        # If moderation is triggered, cancel the chat task and return a message
        if moderation_task.result() == True:
            chat_task.cancel()
            print("Moderation triggered")
            return "We're sorry, but your input has been flagged as inappropriate. Please rephrase your input and try again."

        # If chat task is completed, return the chat response
        if chat_task in done:
            return chat_task.result()

        # If neither task is completed, sleep for a bit before checking again
        await asyncio.sleep(0.1)

def check_image_moderation(image_url):
    response = client.moderations.create(
        model="omni-moderation-latest",
        input=[
            {
                "type": "image_url",
                "image_url": {
                    "url": image_url
                }
            }
        ]
    )

    # Extract the moderation categories and their flags
    results = response.results[0]
    flagged_categories = vars(results.categories)
    flagged = results.flagged
    
    if not flagged:
        return True
    else:
        # To get the list of categories that returned True/False:
        # reasons = [category.capitalize() for category, is_flagged in flagged_categories.items() if is_flagged]
        return False

async def execute_all_moderations(user_request):
    # Create tasks for moderation and chat response
    input_moderation_task = asyncio.create_task(check_moderation_flag(user_request))
    chat_task = asyncio.create_task(get_chat_response(user_request))

    while True:
        done, _ = await asyncio.wait(
            [input_moderation_task, chat_task], return_when=asyncio.FIRST_COMPLETED
        )

        # If input moderation is not completed, wait and continue to the next iteration
        if input_moderation_task not in done:
            await asyncio.sleep(0.1)
            continue

        # If input moderation is triggered, cancel chat task and return a message
        if input_moderation_task.result() == True:
            chat_task.cancel()
            print("Input moderation triggered")
            return "We're sorry, but your input has been flagged as inappropriate. Please rephrase your input and try again."

        # Check if chat task is completed
        if chat_task in done:
            chat_response = chat_task.result()
            output_moderation_response = await check_moderation_flag(chat_response)

            # Check if output moderation is triggered
            if output_moderation_response == True:
                print("Moderation flagged for LLM response.")
                return "Sorry, we're not permitted to give this answer. I can help you with any general queries you might have."
            
            print('Passed moderation')
            return chat_response

        # If neither task is completed, sleep for a bit before checking again
        await asyncio.sleep(0.1)

# Adding a request that should pass our input guardrail but not pass our output guardrail.
interesting_request = "Describe a scene from a violent movie in detail."

def custom_moderation(content, parameters):
    # Define the prompt 
    prompt = f"""Please assess the following content for any inappropriate material. You should base your assessment on the given parameters.
    Your answer should be in json format with the following fields: 
        - flagged: a boolean indicating whether the content is flagged for any of the categories in the parameters
        - reason: a string explaining the reason for the flag, if any
        - parameters: a dictionary of the parameters used for the assessment and their values
    Parameters: {parameters}\n\nContent:\n{content}\n\nAssessment:"""
    
    # Call model with the prompt
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        response_format={ "type": "json_object" },
        messages=[
            {"role": "system", "content": "You are a content moderation assistant."},
            {"role": "user", "content": prompt}
        ]
    )
    
    # Extract the assessment from the response
    assessment = response.choices[0].message.content
    
    return assessment

# Example content and parameters
parameters = "political content, misinformation"