7x31
/
ChatGPT-Next-Web
mirror of https://github.com/Yidadaa/ChatGPT-Next-Web.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,753 Commits 42 Branches 78 Tags 114 MiB
Commit Graph

31 Commits

Author SHA1 Message Date
ryanhex53 b844045d23 Custom model names can include the `@` symbol by itself. 
To specify the model's provider, append it after the model name using `@` as before.

This format supports cases like `google vertex ai` with a model name like `claude-3-5-sonnet@20240620`.

For instance, `claude-3-5-sonnet@20240620@vertex-ai` will be split by `split(/@(?!.*@)/)` into:

`[ 'claude-3-5-sonnet@20240620', 'vertex-ai' ]`, where the former is the model name and the latter is the custom provider.
 2024-11-05 07:44:12 +00:00
frostime 150fc84b9b ✨ feat(model): 增加 sorted 字段，并使用该字段对模型列表进行排序 
1. 在 Model 和 Provider 类型中增加 sorted 字段(api.ts)
2. 默认模型在初始化的时候，自动设置默认 sorted 字段，从 1000 开始自增长(constant.ts)
3. 自定义模型更新的时候，自动分配 sorted 字段(model.ts)
 2024-08-05 19:43:32 +08:00
frostime b023a00445 🔨 refactor(model): 更改原先的实现方法，在 collect table 函数后面增加额外的 sort 处理 2024-08-05 16:37:22 +08:00
frostime 8a4b8a84d6 ✨ feat: 调整模型列表，将自定义模型放在前面显示 2024-08-03 17:16:05 +08:00
Mr. Z c4334d4e5f
Update model.ts 2024-07-25 20:03:54 +08:00
Mr. Z 5c04d3c5ea
Change method 2024-07-25 17:59:15 +08:00
Mr. Z aa4e855012
Compatibility changes 2024-07-22 16:41:11 +08:00
Mr. Z 2fd68bcac3
Fix defaultModel undefined error 2024-07-21 16:42:34 +08:00
lloydzhou 46d3e7884b hotfix: bytedance custom models 2024-07-12 22:53:39 +08:00
lloydzhou 9203870df5 hotfix: using custom models, create custom provider 2024-07-12 20:19:36 +08:00
lloydzhou 5e7254e8dc hotfix: doubao display name 2024-07-11 14:46:12 +08:00
lloydzhou b3023543d6 update 2024-07-09 16:55:33 +08:00
lloydzhou c229d2c3ce merge main 2024-07-09 16:53:15 +08:00
lloydzhou 71af2628eb hotfix: old AZURE_URL config error: "DeploymentNotFound". #4945 #4930 2024-07-09 00:32:18 +08:00
Dogtiti 1caa61f4c0 feat: swap name and displayName for bytedance in custom models 2024-07-06 22:59:20 +08:00
lloydzhou 31d9444264 hotfix 2024-07-04 19:38:26 +08:00
lloydzhou 97aa72ec5b hotfix ts 2024-07-04 08:36:25 +00:00
lloydzhou a68341eae6 include providerId in fullName 2024-07-04 16:11:37 +08:00
lloydzhou aa08183439 hotfix 2024-07-04 16:03:35 +08:00
lloydzhou b9ffd50992 using <modelName>@<providerName> as fullName in modelTable 2024-07-04 15:44:36 +08:00
lloydzhou e7b16bfbc0 add function to check model is available 2024-07-04 15:30:24 +08:00
butterfly b3e856df1d feat: fix 1)the property named 'role' of the first message must be 'user' 2)if default summarize model 'gpt-3.5-turbo' is blocked, use currentModel instead 3)if apiurl&apikey set by location, useCustomConfig would be opened 2024-05-06 19:26:39 +08:00
Wayland Zhan c96e4b7966 feat: Support a way to define default model by adding DEFAULT_MODEL env. 2024-04-19 06:57:15 +00:00
butterfly 79f342439a feat: Solve the problem of using openai interface protocol for user-defined claude model & add some famous webdav endpoints 2024-04-09 20:49:51 +08:00
H0llyW00dzZ e9def2cdc5
Refactor [Model] [LLM Api] Chaining Model 
- [+] refactor(model.ts): change forEach loop to arrow function for readability and consistency
- [+] fix(model.ts): mark 'provider' property as optional in modelTable type
- [+] fix(model.ts): use optional chaining when assigning provider property in modelTable
 2023-12-25 01:12:44 +07:00
Fred Liang 45798f993d
fix: fix type errors 2023-12-24 02:39:13 +08:00
Fred Liang 778e88cb56
chore: resolve conflict 2023-12-24 02:15:30 +08:00
Yidadaa 45b88ebb2a feat: close #3304 use `=` instead of `:` to map model name in CUSTOM_MODELS 2023-11-19 18:34:39 +08:00
Yidadaa dc7159a450 feat: close #3301 enable or diable default models with -all / +all 2023-11-19 18:32:54 +08:00
Yidadaa a5a1f2e8ad feat: CUSTOM_MODELS support mapper 2023-11-12 00:46:21 +08:00
Yidadaa d93f05f511 feat: close #3187 use CUSTOM_MODELS to control model list 2023-11-09 03:01:29 +08:00