[BUG] ios及web端 ollama 模型无法加载

[fsleo]

在最新版本(v181)中，使用ollama本地部署的模型,在 ios 端和 web 端无法加载模型，然而 MacOs app 及 安卓设备中使用是可以的.

进一步测试,我发现在网页端,用 http://localhost:11434 地址,在本机运行 ollama serve 是可以的.但是,如果 ollama serve 在别的电脑或在服务器上运行,指定ip 加端口,就不能加载(注,macOSapp 和安卓端可以)按F12可以看到报下面的错误: renderer.js:154 Mixed Content: The page at 'https://web.chatboxai.app/' was loaded over HTTPS, but requested an insecure resource 'http://xxx.xxx.xxx.xxx:11434/api/tags'. This request has been blocked; the content must be served over HTTPS.

在终端执行: curl http://xxx.xxx.xxx.xxx:11434/api/tags {"models":[{"name":"qwen2.5-coder:3b","model":"qwen2.5-coder:3b","modified_at":"2025-01-09T17:56:19.188471751Z","size":1929912584,"digest":"e7149271c2969e2737cec50f58393671d690a6f99789d1a776c916efeb11fa98","details":{"parent_model":"","format":"gguf","family":"qwen2","families":["qwen2"],"parameter_size":"3.1B","quantization_level":"Q4_K_M"}},{"name":"qwen2.5-coder:7b","model":"qwen2.5-coder:7b","modified_at":"2025-01-09T06:46:00.476191501Z","size":4683087519,"digest":"2b0496514337a3d5901f1d253d01726c890b721e891335a56d6e08cedf3e2cb0","details":{"parent_model":"","format":"gguf","family":"qwen2","families":["qwen2"],"parameter_size":"7.6B","quantization_level":"Q4_K_M"}}]}