The first question on the defense side will be where the spec is going. Thanks to AI_API_BASE_URL, it seems to be working with a local model in a closed network, is that correct, have you tested it? If so, it should be at the top of the README.
Yes that is way I have added this. It could work any OpenAI compatible model or router. I have tested it with Kimi and Qwen. You can bring your own tuned model which is better if you are doing specific work.
The first question on the defense side will be where the spec is going. Thanks to AI_API_BASE_URL, it seems to be working with a local model in a closed network, is that correct, have you tested it? If so, it should be at the top of the README.
Yes that is way I have added this. It could work any OpenAI compatible model or router. I have tested it with Kimi and Qwen. You can bring your own tuned model which is better if you are doing specific work.