spring-projects / spring-projects/spring-ai
Adding support for OpenAI's real-time model
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 9.5k
- Forks
- 2.9k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 6
Description
Added support for OpenAI realtime model, which is built on Websockets
Additionally, if Spring AI can provide a more convenient and rapid way to integrate Spring Websocket, it should be very helpful for developers
Azure's Samples about realtime model
https://github.com/Azure-Samples/aoai-realtime-audio-sdk
The following is excerpted from the Readme
/realtime is built on the WebSockets API to facilitate fully asynchronous streaming communication between the end user and model. It's designed to be used in the context of a trusted, intermediate service that manages both connections to end users and model endpoint connections; it is not designed to be used directly from untrusted end user devices, and device details like capturing and rendering audio data are outside the scope of the /realtime API.
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 by reviewing the /realtime WebSockets API description and the linked Azure realtime audio SDK sample to understand the required asynchronous model connection. Define the Spring AI integration surface and determine what a convenient Spring WebSocket path should provide; done means OpenAI's realtime model is supported with a documented integration approach.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, spring
- Domain
- ai, backend-api-design
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100