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

New tools and features in the Responses API

openai.com

Post reply on HN
Print view View original

31–35 of 35 posts

Re: New tools and features in the Responses API

#31

Post by nknj »

swyx wrote: post #22
nknj wrote: post #18

Earlier quoted context omitted.

one additional difference between chat and responses is the number model turns a single api call can make. chat completions is a single turn api primitive -- which means it can talk to the model just once. responses is capable of making multiple model turns and tool calls in a single api call. for example, you can give the responses api access to 3 tools: a vector store with some user memories (file_search), the shop…

i think the original intent of responses api was also to unify the realtime experiences into responses - is that accurate?

we expect responses and realtime to be our 2 core api primitives long term — responses for turn by turn interactions and realtime for models requiring low latency bidirectional streams to/from the apps/models.

Re: New tools and features in the Responses API

#32

Post by knowsuchagency »

zoogeny wrote: post #28
zvitiate wrote: post #15

Earlier quoted context omitted.

Google actually switched to an OpenAI system for 2.5 Pro's Chain-of-Thought yesterday on the Gemini app and AI Studio ("I did this; I did that. etc"). Apparently it still shows via API, but no clear how long. Also, in my experience, if you select the "Canvas" output, you still get the old style CoT. And yes, the above is true even if you are ULTRA. You can still view your old thinking traces from prior turns and conv…

My heart just broke to hear this. Although I honestly don't read the thinking output very often. But I had been cheekily copy-n-pasting the info for my own records.

I agree, but there's always Deepseek. They're publishing and open-sourcing more than anyone these days.

Re: New tools and features in the Responses API

#33

Post by swyx »

nknj wrote: post #31
swyx wrote: post #22

Earlier quoted context omitted.

i think the original intent of responses api was also to unify the realtime experiences into responses - is that accurate?

we expect responses and realtime to be our 2 core api primitives long term — responses for turn by turn interactions and realtime for models requiring low latency bidirectional streams to/from the apps/models.

thank you for the correction!

Re: New tools and features in the Responses API

#34

Post by akgfab »

nknj wrote: post #30
beklein wrote: post #24

Earlier quoted context omitted.

On the announcement page they are saying that "...introducing updates to the file search tool that allow developers to perform searches across multiple vector stores..." . On the docs, I still find this limitation: "At the moment, you can search in only one vector store at a time, so you can include only one vector store ID when calling the file search tool." Anybody knows how searching multiple vector stores is impl…

sorry about the error in the docs. we're removing that call out. `"vector_store_ids": [" ", " "]` is exactly right. only 2 vector stores are supported at the moment.

2 feels quite arbitrary and honestly not that much of an improvement. Any plans to up that limit?

Re: New tools and features in the Responses API

#35

Post by andrewrn »

brittlewis12 wrote: post #14
andrewrn wrote: post #6

It was never really clear what the difference between the chat and responses APIs were. Anyone know the difference?

chat completions is stateless — you must provide the entire conversation history with each new message; openai stores nothing (at least nothing that the downstream product _can use_) beyond the life of the request. responses api, by contrast, is stateful — only send the latest message, and openai stores the conversation history, while keeping track of other details on behalf of the calling app, like parallel tool cal…

This is very enlightening. You're right then, it does seem to partially be a strategic moat-building move by OpenAI
Post reply on HN