Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Native JSON Output from GPT-4

yonom.substack.com

Post reply on HN
Print view View original

21–30 of 258 posts

Re: Native JSON Output from GPT-4

#21

Post by isoprophlex »

have_faith wrote: post #15
tornato7 wrote: post #7

Earlier quoted context omitted.

IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.

How would a tweaked temp enforce a non broken output exactly?

Not traditional temperature, maybe the parent worded it somewhat obtusely. Anyway, to disambiguate...

I think it works something like this: You let something akin to a json parser run with the output sampler. First token must be either '{' or '['; then if you see [ has the highest probability, you select that. Ignore all other tokens, even those with high probability.

Second token must be ... and so on and so on.

Guarantee for non-broken (or at least parseable) json

Re: Native JSON Output from GPT-4

#22

Post by stavros »

thorum wrote: post #2

The JSON schema not counting toward token usage is huge, that will really help reduce costs.

> Under the hood, functions are injected into the system message in a syntax the model has been trained on. This means functions count against the model's context limit and are billed as input tokens. If running into context limits, we suggest limiting the number of functions or the length of documentation you provide for function parameters.

Re: Native JSON Output from GPT-4

#23

Post by woodrowbarlow »

tornato7 wrote: post #7
minimaxir wrote: post #3

After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary. As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical…

IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.

the linked article hypothesizes:

> I assume OpenAI’s implementation works conceptually similar to jsonformer, where the token selection algorithm is changed from “choose the token with the highest logit” to “choose the token with the highest logit which is valid for the schema”.

Re: Native JSON Output from GPT-4

#25

Post by minimaxir »

swyx wrote: post #19

i think people are underestimating the potential here for agents building - it is now a lot easier for GPT4 to call other models, or itself. while i was taking notes for our emergency pod yesterday ( https://www.latent.space/p/function-agents ) we had this interesting debate with Simon Willison on just how many functions will be supplied to this API. Simon thinks it will be "deep" rather than "wide" - eg a few functi…

"Trivial" is misleading. From OpenAI's docs and demos, the full ReAct workflow is an order of magnitude more difficult than typical ChatGPT API usage with a new set of constaints (e.g. schema definitions)

Even OpenAI's notebook demo has error handling workflows which was actually necessary since ChatGPT returned incorrect formatted output.

Re: Native JSON Output from GPT-4

#28

Post by majormajor »

swyx wrote: post #19

i think people are underestimating the potential here for agents building - it is now a lot easier for GPT4 to call other models, or itself. while i was taking notes for our emergency pod yesterday ( https://www.latent.space/p/function-agents ) we had this interesting debate with Simon Willison on just how many functions will be supplied to this API. Simon thinks it will be "deep" rather than "wide" - eg a few functi…

GPT-4 was already a massive improvement on 3.5 in terms of replying consistently in a certain JSON structure - I often don't even need to give examples, just a sentence describing the format.

It's great to see they're making it even better, but where I'm currently hitting the limit still in GPT-4 for "shelling out" is about it being truly "creative" or "introspective" about "do I need to ask for clarifications" or "can I find a truly novel away around this task" type of things vs "here's a possible but half-baked sequence I'm going to follow".

Re: Native JSON Output from GPT-4

#29

Post by sanxiyn »

have_faith wrote: post #15
tornato7 wrote: post #7

Earlier quoted context omitted.

IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.

How would a tweaked temp enforce a non broken output exactly?

It's not temperature, but sampling. Output of LLM is probabilistic distribution over tokens. To get concrete tokens, you sample from that distribution. Unfortunately, OpenAI API does not expose the distribution. You only get the sampled tokens.

As an example, on the link JSON schema is defined such that recipe ingredient unit is one of grams/ml/cups/pieces/teaspoons. LLM may output the distribution grams(30%), cups(30%), pounds(40%). Sampling the best token "pounds" would generate an invalid document. Instead, you can use the schema to filter tokens and sample from the filtered distribution, which is grams(50%), cups(50%).

Post reply on HN