We need to do some work before we can also just store them simply as markdown files.
Regarding open models: what is the go-to way for me to make Surf run with qwen3-vl? Ollama?
As far as I understand any endpoint that supports the completions API will work?
https://github.com/deta/surf/blob/main/docs/AI_MODELS.md
If I attach image context will it be provided to qwen3-vl? Or does this only work with the "main" models like OpenAI, Anthropic, Gemini and so on?
Yes, we support any endpoint that supports the completions API. And yes, Ollama might be the easiest to setup. The images should also work with qwen3-vl.
But if you run into any issues, please feel free to submit a bug report https://github.com/deta/surf/issues
Edit: fixed github issues link
https://www.aljazeera.com/news/2025/9/8/six-killed-in-nepal-...
I also work with an Electron app and we also do local embeddings and most of the CPU intensive work happens in nodejs addons written in Rust and using Neon (https://neon-rs.dev very grateful for this lib). This is a nice balance for us.
From the CTO, Source: https://x.com/dok2001/status/1990791419653484646