QAnything
QAnything copied to clipboard
[BUG] 用完全兼容OpenAI API的大模型作为后端运行,提问的时候会出错
是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?
- [X] 我已经搜索过FAQ | I have searched FAQ
当前行为 | Current Behavior
我尝试直接用OpenAI的API来运行,没有问题, 然而换成了一个完全兼容OpenAI API的大模型来运行,就会报错(Linux环境和windows环境都会报错)。 (尝试过把这个大模型放在其他平台:如ChatGPT-Next-Web,没有兼容问题)
期望行为 | Expected Behavior
帮忙解答一下技术上是否有强制使用OPENAI的限制?
运行环境 | Environment
- OS: WIN11
- NVIDIA Driver: 551.61
- CUDA: 12.4
- docker: 25.0.3
- docker-compose: v2.24.6-desktop.1
- NVIDIA GPU: RXT 2060(or RTX 4080)
- NVIDIA GPU Memory: 6GB
QAnything日志 | QAnything logs
No response
复现方法 | Steps To Reproduce
No response
备注 | Anything else?
No response