You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
docs: refactor model naming and update docs (#166)
- Update documentation to reflect the change from `gpt-3.5-turbo` to `gpt-4-turbo` and add mention of custom models
- Remove references to `openai.model_name` in README and code, replacing with `openai.model`
- Delete the `openai.model_name` configuration option from `config_list.go`
- Remove the `model_name` flag binding from `config_set.go`
Signed-off-by: Bo-Yi Wu <appleboy.tw@gmail.com>
Copy file name to clipboardExpand all lines: README.md
+2-3Lines changed: 2 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -83,7 +83,7 @@ This will create a `.codegpt.yaml` file in your home directory ($HOME/.config/co
83
83
***openai.base_url**: replace the default base URL (`https://api.openai.com/v1`).
84
84
***openai.api_key**: generate API key from [openai platform page](https://platform.openai.com/account/api-keys).
85
85
***openai.org_id**: Identifier for this organization sometimes used in API requests. see [organization settings](https://platform.openai.com/account/org-settings). only for `openai` service.
86
-
***openai.model**: default model is `gpt-3.5-turbo`, you can change to `gpt-4` or [other available model list](https://github.com/appleboy/CodeGPT/blob/bf28f000463cfc6dfa2572df61e1b160c5c680f7/openai/openai.go#L18-L38).
86
+
***openai.model**: default model is `gpt-3.5-turbo`, you can change to `gpt-4-turbo` or other custom model (Groq or OpenRouter provider).
87
87
***openai.proxy**: http/https client proxy.
88
88
***openai.socks**: socks client proxy.
89
89
***openai.timeout**: default http timeout is `10s` (ten seconds).
@@ -92,7 +92,6 @@ This will create a `.codegpt.yaml` file in your home directory ($HOME/.config/co
92
92
***git.diff_unified**: generate diffs with `<n>` lines of context, default is `3`.
93
93
***git.exclude_list**: exclude file from `git diff` command.
94
94
***openai.provider**: default service provider is `openai`, you can change to `azure`.
95
-
***openai.model_name**: model deployment name (for azure).
96
95
***output.lang**: default language is `en` and available languages `zh-tw`, `zh-cn`, `ja`.
97
96
***openai.top_p**: default top_p is `1.0`. see reference [top_p](https://platform.openai.com/docs/api-reference/completions/create#completions/create-top_p).
98
97
***openai.frequency_penalty**: default frequency_penalty is `0.0`. see reference [frequency_penalty](https://platform.openai.com/docs/api-reference/completions/create#completions/create-frequency_penalty).
@@ -112,7 +111,7 @@ Update your config file.
112
111
codegpt config set openai.provider azure
113
112
codegpt config set openai.base_url https://xxxxxxxxx.openai.azure.com/
114
113
codegpt config set openai.api_key xxxxxxxxxxxxxxxx
115
-
codegpt config set openai.model_name xxxxx-gpt-35-turbo
114
+
codegpt config set openai.model xxxxx-gpt-35-turbo
Copy file name to clipboardExpand all lines: cmd/config_list.go
-1Lines changed: 0 additions & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -30,7 +30,6 @@ var availableKeys = map[string]string{
30
30
"openai.max_tokens": "the maximum number of tokens to generate in the chat completion.",
31
31
"openai.temperature": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.",
32
32
"openai.provider": "service provider, only support 'openai' or 'azure'",
33
-
"openai.model_name": "model deployment name for Azure cognitive service",
0 commit comments