Is your feature request related to a problem? Please describe.
Would it be possible to support websocket mode in OpenAIResponsesChatGenerator (or a variant of the haystack component)?(https://developers.openai.com/api/docs/guides/websocket-mode) This would enable lower latency for long agentic tasks.
Describe the solution you'd like
A haystack component, that keeps a persistent websocket connection, and interacts with OpenAI backend via wss connection. Other AI frameworks have introduced support for this, e.g. vercel/ai#12775
👋 Hello there! This issue will be handled internally and isn’t open for external contributions. If you’d like to contribute, please take a look at issues labeled contributions welcome or good first issue. We’d really appreciate it!
Is your feature request related to a problem? Please describe.
Would it be possible to support websocket mode in OpenAIResponsesChatGenerator (or a variant of the haystack component)?(https://developers.openai.com/api/docs/guides/websocket-mode) This would enable lower latency for long agentic tasks.
Describe the solution you'd like
A haystack component, that keeps a persistent websocket connection, and interacts with OpenAI backend via wss connection. Other AI frameworks have introduced support for this, e.g. vercel/ai#12775
👋 Hello there! This issue will be handled internally and isn’t open for external contributions. If you’d like to contribute, please take a look at issues labeled contributions welcome or good first issue. We’d really appreciate it!