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

21–30 of 35 posts

Re: New tools and features in the Responses API

#21

Post by OutOfHere »

nknj wrote: post #18
brittlewis12 wrote: post #14

Earlier quoted context omitted.

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…

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…

What are my choices for using a custom tool? Does it come down to: function calling (single turn), MCP (multi-turn via Responses)? What else are my choices?

Why would anyone want to use Responses statelessly? Just trying to understand.

Re: New tools and features in the Responses API

#22

Post by swyx »

nknj wrote: post #18
brittlewis12 wrote: post #14

Earlier quoted context omitted.

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…

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?

Re: New tools and features in the Responses API

#24

Post by beklein »

nknj wrote: post #17
jasongill wrote: post #5

I wish OpenAI would provide more clarity about the Assistants API deprecation, which has been announced as being sunset in spring of 2026 and replaced by the Responses API, but still no other updates on the timeline or migration plan. Prior to the release of the Responses API, the Assistants API was the best way (for our use cases, at least) to interact with OpenAI's API, so hopefully some clarity on the plan for it…

I hear you and really appreciate the patience here. We're almost ready to share a migration guide. Today, we closed the gap between Assistants and Responses by launching Code Interpreter and support for multiple vector stores in File Search. We still need to add support for Assistants and Threads objects to Responses before we can give devs a simple migration path. Working on this actively and hope to have all of thi…

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 implemented? The obvious plan would be to allow something like:

  "vector_store_ids": ["", "", ...]

Re: New tools and features in the Responses API

#25

Post by epiccoleman »

Doohickey-d wrote: post #16
rafram wrote: post #11

Earlier quoted context omitted.

I may be giving Gemini too much credit, actually - seems like its "reasoning" may be a summary as well.

They changed it yesterday or so: it used to show the actual reasoning, now it no longer does. And the reasoning was quite useful to see if it was going down the wrong track, the summary is much less so.

That's disappointing. I was getting a lot of utility from reading through the thoughts returned by Gemini when I used it in Cursor - occasionally even learning something new from its stream of "consciousness". Obfuscating the information because it can be used to train competitors seems misguided, if understandable.

Re: New tools and features in the Responses API

#26

Post by mritchie712 »

jasongill wrote: post #5

I wish OpenAI would provide more clarity about the Assistants API deprecation, which has been announced as being sunset in spring of 2026 and replaced by the Responses API, but still no other updates on the timeline or migration plan. Prior to the release of the Responses API, the Assistants API was the best way (for our use cases, at least) to interact with OpenAI's API, so hopefully some clarity on the plan for it…

we were using it for our agent in https://www.definite.app/ and I've been expecting it to die for almost a year considering the lack of updates.

We switched over to https://ai.pydantic.dev/ which I really like. LLM agnostic and the team is very receptive to feedback.

Re: New tools and features in the Responses API

#28

Post by zoogeny »

zvitiate wrote: post #15
rafram wrote: post #7

> Encrypted reasoning items: Customers eligible for Zero Data Retention (ZDR) can now reuse reasoning items across API requests So, so weird that they still don't want you to see their models' reasoning process, to the point that even highly trusted organizations with ZDR contracts only get them in a black-box encrypted form. Gemini has no issue showing its work. Why can't OpenAI?

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.

Re: New tools and features in the Responses API

#29

Post by vessenes »

epiccoleman wrote: post #25
Doohickey-d wrote: post #16

Earlier quoted context omitted.

They changed it yesterday or so: it used to show the actual reasoning, now it no longer does. And the reasoning was quite useful to see if it was going down the wrong track, the summary is much less so.

That's disappointing. I was getting a lot of utility from reading through the thoughts returned by Gemini when I used it in Cursor - occasionally even learning something new from its stream of "consciousness". Obfuscating the information because it can be used to train competitors seems misguided, if understandable.

Agreed. Right now deepseek’s R1 has uncensored stream of consciousness in open weights. I think it’s interesting that teams feel the streams should be proprietary. They must be doing something a little different than R1, or it wouldn’t be worth the extra engineering work.

Re: New tools and features in the Responses API

#30

Post by nknj »

beklein wrote: post #24
nknj wrote: post #17

Earlier quoted context omitted.

I hear you and really appreciate the patience here. We're almost ready to share a migration guide. Today, we closed the gap between Assistants and Responses by launching Code Interpreter and support for multiple vector stores in File Search. We still need to add support for Assistants and Threads objects to Responses before we can give devs a simple migration path. Working on this actively and hope to have all of thi…

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.

Post reply on HN