Re:All I Want for Xmas Is Your Secrets: LangGrinch Hits Lang...
by majormajor on Thursday December 25, 2025 @05:28PM
(#46387430)
IME you could get reliable JSON or other easily-parsable output formats out of OpenAI's going back at least to GPT3.5 or 4 in early 2023. I think that was a bit after LangChain's release but I don't recall hitting problems that I needed to add a layer around in order to do "agent"-y things ("dispatch this to this specialized other prompt-plus-chatgpt-api-call, get back structured data, dispatch it to a different specialized prompt-plus-chatgpt-api-call") before it was a buzzword.
Re:All I Want for Xmas Is Your Secrets: LangGrinch Hits Lang...
by nostrebored on Thursday December 25, 2025 @09:55PM
(#46388800)
Can guarantee this was not true for any complicated extraction. You could reliably get it to output json but not the json you wanted
Even on smallish ~50k datasets error was still very high and interpretation of schema was not particularly good.
Re:All I Want for Xmas Is Your Secrets: LangGrinch Hits Lang...
by avaer on Friday December 26, 2025 @01:04AM
(#46389591)
It's still not true for any complicated extraction. I don't think I've ever shipped a successful solution to anything serious that relied on freeform schema say-and-pray with retries.
Re:All I Want for Xmas Is Your Secrets: LangGrinch Hits Lang...
by avaer on Friday December 26, 2025 @01:01AM
(#46389578)
To this day many good models don't support structured outputs (say Opus 4.5) so it's not a panacea you can count on in production.
The bigger problem is that LangChain/Python is the least set up to take advantage of strong schemas even when you do have it.
Agree about pillaging for prompts though.
Re:All I Want for Xmas Is Your Secrets: LangGrinch Hits Lang...
by teruakohatu on Friday December 26, 2025 @05:00AM
(#46390753)
> so it's not a panacea you can count on in production.
OpenAI and Gemini models can handle ridiculously complicated and convoluted schemas, if I needed complicated JSON output I wouldn’t use anything that didn’t guarantee it.
I have pushed Gemini 2.5 Pro further than I thought possible when it comes to ridiculously over complicated (by necessity) structured output.
I think structured output with schema validation mostly replaces the need for complex prompt frameworks. I do look at the LC source from time to time because they do have good prompts backed into the framework.