14

The problem with this approach is the unnecessarily high frequency of requests hitting the endpoint. Such an approach will unnecessarily add to compute requirements.

Imagine abusive and normal usage requests hitting the same endpoint, the decision making happening on OpenAI side whether to pass the request for generation (think about the hold time), or deny them.

Then the complexity of API response; one response for denial while another entirely different for generation.

Compare this to the scenario where only filtered requests are hitting the generation endpoint (obviously no unnecessary ones) the decision making happening on devs’ systems.

The simplicity of response; devs know what kind of responses to expect from each endpoint.

+ Edit: Integrated approach will also hamper devs from bringing their own moderation system, which could be faster/better.

3 Likes
15

Communication is key.
Who should use the moderation endpoint when, how and what will happen if there are problems.
Then everybody can make their own choices.

I would leave things as they are because I think the rules are common sense.

16

The problem with making two API calls every time instead of one is the latency, and degrading performance for no reason.

I can see use cases where developers might have a need to call the ‘moderation’ endpoint standalone, with no intent to RUN the query if it passes moderation, but just because that’s true doesn’t mean that 100% of all of the most common usage patterns of the API should always require two back to back HTTP requests.

The obvious solution is a “moderate=true” flag on the completions endpoint, that defaults to true.

18

Yes indeed, the additional HTTP call adds latency.

I think one of the most common use cases is “chat bots” where apps take raw input from end users, and so 100% of those calls would need to be sent thru moderation (according to many peoples interpretations of the vague policy docs), and so if that’s the case the rational choice for API design is to have moderation built into the ‘completions’ call, as an option that defaults to true.

I’d like to say to the API, “block this if it violates OpenAI policy”, and don’t ding my API key. So maybe the more applicable parameter name is “ding=false”. lol.

19

This seems like a lot of extra work and compromises just to prevent mere milliseconds of latency.

When you are building a tool for all programmers the less assumptions & opinions the better.

1 Like
20

I can agree with that, I think it’s worth delving a bit into this.

This is absolutely true, let’s remember that the moderation endpoint is an AI classifier. It’s probably not as resource-intensive as GPT, but it will still require GPUs, and those are currently in short supply.

1 Like
21

Not just that. At the scale at which OpenAI receives requests per sec, even a slight hold can induce a huge backlog.

As the saying goes “the more moving parts, the more things can go wrong”.

1 Like
22

Fair point,

Although I think it’s worth mentioning that OpenAI is already passing the input, output, and generated title on ChatGPT through the moderation endpoint, so they do already know how to successfully put those cogs together.

1 Like
23

ChatGPT is an end-user product and that uses the moderation endpoint really well.

also,

3 Likes
24

Don’t you think cutting the number of requests per second in half is a good idea? lol. I do.

25

When developing a tool for everyone, also the most commonly occurring usage patterns become particular relevant. If most of the time a call does moderation+completion, that’s a pretty good tip you need an endpoint that encapsulates exactly that.

26

I 100% agree with @sps

But I fail to see the logic here

Why would this cut the number of requests per second in half?

1 Like
28

“API Endpoints with Integrated Content Moderation” take one HTTP request. Without integration it’s two.

29

You made a whole lot of assumptions I wasn’t implying. I’m just saying have a “moderate=true” flag, and if I set that the server can simply throw a bad request error, with the reason. It’s not mixing responsibilities. It’s good API design. If something takes 10 steps you don’t always tell the API consumers to make 10 HTTP requests. It’s an art not a science.

31

HTTP APIs normally have all kinds of different “reasons” that any particular request can fail. I’m just saying “bad morality” is most certainly one of the reasons the “completions” should be able to fail. And from my 23yrs exp as a dev, I can tell you it’s about 3 lines of code to check this and throw an exception in OpenAI’s implementation. Aside from adding “dontDingMeBro” as an argument.

32

The rate limits are counted per endpoint, using the moderation endpoint is not going to count towards your rate limits on completion requests :laughing:

33

Regardless of academically good API design, Azure already does this. They run filtering on all chat completion requests and return moderation errors from that endpoint.

34

Good point. That would imply an “immoral query” attempt would cost nothing, because they refused to answer it. That’s identical to submitting a moderation endpoint query that gets failed. Currently they already offer the pure moderation endpoint for free. Correct.

35

To me that’s just silly and would result in a lot of unhandled errors

36

Well I think that’s the crux of the issue in these threads. Azure thinks that it’s important enough to strictly enforce all requests should be moderated before running. OpenAI doesn’t, and while OpenAI may punish you if you don’t moderate it, the documentation could certainly be more clear around when to use it and the ramifications of not using it.

1 Like