Built a server to make this OpenAI compatible

#21
by sur4guy101 - opened

Hey — getting Qwen3-VL-Embeddings running locally for RAG was kind of a headache (deps, setup, etc).

I put together a small server that makes it OpenAI-compatible so you can just drop it into existing pipelines.

  • works with standard OpenAI clients
  • handles text + image embeddings
  • runs clean locally (tested on a 5070)

If you’re trying to use this model without fighting setup, this might save you some time.

https://github.com/philmcginty/qwen3-vl-embedding-server

Happy to help if anyone gets stuck setting it up.

Sign up or log in to comment