[Bug] Non -GPT model disable system prompt

[d4renk]

Describe the bug A clear and concise description of what the bug is. Self-deployed large models will automatically inject system-level prompts, resulting in incorrect answers. It should be that only gpt api injects the default system prompt. 自部署大模型会默认注入系统提示 导致回答错误 应该是只有gpt api注入才对 https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/3684 这个pull似乎没有考虑到自部署大模型的情况 V2.10.1 To Reproduce Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error docker deployment and add environment variables. docker部署并添加环境变量

   CUSTOM_MODELS=-all,+Balanced-g4t-offline,+Creative-g4t,+Balanced-g4t,+Precise-g4t,+Creative,+Balanced,+Precise,+Creative-g4t-offline,+Precise-g4t-offline,+Creative-offline,+Balanced-offline,+Precise-offline
   BASE_URL=https://bingai.zklcdc.xyz
   HIDE_USER_API_KEY=1

   Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

Deployment

• [y] Docker
• [ ] Vercel
• [ ] Server

Desktop (please complete the following information):

• OS: [e.g. iOS]
• Browser [e.g. chrome, safari]
• Version [e.g. 22]

Smartphone (please complete the following information):

• Device: [e.g. iPhone6]
• OS: [e.g. iOS8.1]
• Browser [e.g. stock browser, safari]
• Version [e.g. 22]

Additional Logs Add any logs about the problem here. {"messages":[{"role":"system","content":"\nYou are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2021-09\nCurrent model: Balanced-g4t-offline\nCurrent time: 2024/1/31 20:21:45\nLatex inline: $x^2$ \nLatex block: $$e=mc^2$$\n\n"},{"role":"user","content":"hi"}],"stream":true,"model":"Balanced-g4t-offline","temperature":0.5,"presence_penalty":0,"frequency_penalty":0,"top_p":1}

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Title: [Bug] Non -GPT model disable system prompt