deepset-ai / deepset-ai/haystack
Support for websocket mode in OpenAIResponsesChatGenerator
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 26.6k
- Forks
- 3.2k
- Avg merge
- 1d 3h
- Merged PRs (30d)
- 194
Description
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. https://github.com/vercel/ai/pull/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!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the OpenAIResponsesChatGenerator and review the linked OpenAI websocket-mode guide and Vercel implementation for context. The requested result is a Haystack component or variant that maintains a persistent wss connection and supports lower-latency interactions with the OpenAI backend; the issue notes that this work is handled internally.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 20/100