处理url带models的请求 about glm-free-api HOT 9 CLOSED

如果是clone的项目，直接拉最新代码，然后重启即可

from glm-free-api.

base url没有设置正确，请填写到/v1为止，后续的部分不要加。

from glm-free-api.

base url没有设置正确，请填写到/v1为止，后续的部分不要加。

不行的，这个软件它会自动加上models

from glm-free-api.

0|glm-free-api | [2024-05-01 17:46:38.859][warning][server.ts<79,20>] [请求有误]: 正确请求为 POST -> /v1/chat/completions，当前请求为 GET -> /v1//models 请纠正

from glm-free-api.

程序加models没问题，目前最新版本都会返回模型列表，base url尾部不要加/，拼接后就变成//

from glm-free-api.

0|glm-free-api | [2024-05-01 18:17:58.562][info][server.ts<99,28>] -> POST /v1/chat/completions
0|glm-free-api | [2024-05-01 18:17:58.562][info][chat.ts<176,12>] [
0|glm-free-api | { role: 'system', content: 'You are a helpful assistant.' },
0|glm-free-api | { role: 'user', content: 'Test prompt using gpt-3.5-turbo' }
0|glm-free-api | ]
0|glm-free-api | [2024-05-01 18:17:58.563][info][chat.ts<482,10>] 本次请求上传：0个文件
0|glm-free-api | [2024-05-01 18:17:58.563][info][chat.ts<545,10>]
0|glm-free-api | 对话合并：
0|glm-free-api | <|sytstem|>
0|glm-free-api | You are a helpful assistant.
0|glm-free-api | <|user|>
0|glm-free-api | Test prompt using gpt-3.5-turbo
0|glm-free-api | <|assistant|>
0|glm-free-api |
0|glm-free-api | [2024-05-01 18:17:59.835][success][chat.ts<229,12>] Stream has completed transfer 1082ms
0|glm-free-api | [2024-05-01 18:17:59.839][info][server.ts<66,36>] <- POST /v1/chat/completions 1277ms
0|glm-free-api | [2024-05-01 18:17:59.896][debug][server.ts<75,20>] -> GET /v1/models request is not supported - 127.0.0.1
0|glm-free-api | [2024-05-01 18:17:59.897][warning][server.ts<79,20>] [请求有误]: 正确请求为 POST -> /v1/chat/completions，当前请求为 GET -> /v1/models 请纠正
0|glm-free-api | [2024-05-01 18:17:59.898][info][server.ts<84,24>] <- GET /v1/models 2ms

from glm-free-api.

from glm-free-api.

确认版本是否最新，我这边测试正常，models接口在0.0.23版本才加入支持

from glm-free-api.

测试没问题了，我想问一下npm部署怎么进行更新

from glm-free-api.