Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

continue vscode openai-compatible #4278

Open
2 tasks
guyujun opened this issue Feb 21, 2025 · 3 comments
Open
2 tasks

continue vscode openai-compatible #4278

guyujun opened this issue Feb 21, 2025 · 3 comments
Assignees
Labels
area:configuration Relates to configuration options ide:vscode Relates specifically to VS Code extension kind:enhancement Indicates a new feature request, imrovement, or extension "needs-triage"

Comments

@guyujun
Copy link

guyujun commented Feb 21, 2025

Validations

  • I believe this is a way to improve. I'll try to join the Continue Discord for questions
  • I'm not able to find an open issue that requests the same enhancement

Problem

The API provider seems insufficient. Is it possible to add OpenAI-compatible custom methods?

Solution

No response

@dosubot dosubot bot added area:configuration Relates to configuration options ide:vscode Relates specifically to VS Code extension kind:enhancement Indicates a new feature request, imrovement, or extension labels Feb 21, 2025
@guyujun
Copy link
Author

guyujun commented Feb 21, 2025

https://ark.cn-beijing.volces.com/api/v3/

volcengine is a faster/popular API provider in china

@forrestgao
Copy link

{
"title": "DeepSeek R1",
"model": "EP-",
"contextLength": 128000,
"apiKey": "
",
"apiBase": "https://ark.cn-beijing.volces.com/api/v3",
"Provider": "OpenAI"
} Work for me, I can successfully ask questions and receive intelligent responses, but I still encounter the following error message every time I open VSCode:HTTP 401 Unauthorized from https://api.openai.com/v1/completions { "error": { "message": "Incorrect API key provided……

@guyujun
Copy link
Author

guyujun commented Feb 23, 2025

I achieve this by utilizing v1 instead of v3, and it’s crucial to enable the useLegacyCompletionsEndpoint option. i m not sure temperature work or not.

{
      "title": "deepseek-r1",
      "model": "ep-20250214031836-p2wfd",
      "contextLength": 128000,
      "apiKey": "",
      "apiBase": "https://ark.cn-beijing.volces.com/api/v1/",
      "provider": "openai",
      "options.temperature": 0.6,
      "useLegacyCompletionsEndpoint": false
    },
    {
      "title": "deepseek-v3",
      "model": "ep-20250214020016-7c8z9",
      "contextLength": 128000,
      "apiKey": "",
      "apiBase": "https://ark.cn-beijing.volces.com/api/v1/",
      "provider": "openai",
      "options.temperature": 0.6,
      "useLegacyCompletionsEndpoint": false
    }

hope it helps for you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
area:configuration Relates to configuration options ide:vscode Relates specifically to VS Code extension kind:enhancement Indicates a new feature request, imrovement, or extension "needs-triage"
Projects
None yet
Development

No branches or pull requests

3 participants