-
-
Notifications
You must be signed in to change notification settings - Fork 4.3k
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
feat: add Google Gemini Pro support #826
Conversation
controller/relay-gemini-chat.go
Outdated
choice.FinishReason = &stopFinishReason | ||
var response ChatCompletionsStreamResponse | ||
response.Object = "chat.completion.chunk" | ||
response.Model = "gemini" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
gemini-pro
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Gemini Ultra 未来复用代码即可
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
怀疑 Gemini Ultra 的URL应该会是 https://generativelanguage.googleapis.com/v1beta/models/gemini-ultra:generateContent
,所以这里不写死pro
.
现在开始处理该 PR |
Thx~ |
* fest: Add Google Gemini Pro, fix songquanpeng#810 * fest: Add tooling to Gemini; Add OpenAI-like system prompt to Gemini * refactor: removing unused if statement * fest: Add dummy model message for system message in gemini model * chore: update implementation --------- Co-authored-by: JustSong <[email protected]>
* feat: add Google Gemini Pro support (songquanpeng#826) * fest: Add Google Gemini Pro, fix songquanpeng#810 * fest: Add tooling to Gemini; Add OpenAI-like system prompt to Gemini * refactor: removing unused if statement * fest: Add dummy model message for system message in gemini model * chore: update implementation --------- Co-authored-by: JustSong <[email protected]> * fix: fix Gemini stream problem * fix: fix xunfei panic error (close songquanpeng#820) * fix: try to return a more meaningful error message (close songquanpeng#817) * feat: reset image num to 1 when not given (songquanpeng#821) * Update relay-image.go * fix: reset image num to 1 when not given --------- Co-authored-by: JustSong <[email protected]> * feat: able to set sqlite busy_timeout (songquanpeng#818) * add sqlite busy_timeout=3000 * chore: update impl --------- Co-authored-by: JustSong <[email protected]> * feat: update ali relay implementation (songquanpeng#830) * 修改通译千问最新接口:1.删除history参数,改用官方推荐的messages参数 2.整理messages参数顺序,补充必要上下文信息 3.用autogen调试测试通过 * chore: update impl --------- Co-authored-by: JustSong <[email protected]> * feat: add condition to validate n value for non-Azure channels (songquanpeng#775) - Add a condition to validate the n value only for non-Azure channels, ensuring it falls within the acceptable range. - Fix Azure compatibility * docs: update readme * docs: update readme * fix: fix gemini panic (close songquanpeng#833) * fix: fix max_tokens check --------- Co-authored-by: David Zhuang <[email protected]> Co-authored-by: JustSong <[email protected]> Co-authored-by: Ghostz <[email protected]> Co-authored-by: Calcium-Ion <[email protected]> Co-authored-by: Oliver Lee <[email protected]> Co-authored-by: ShinChven ✨ <[email protected]>
* fest: Add Google Gemini Pro, fix songquanpeng#810 * fest: Add tooling to Gemini; Add OpenAI-like system prompt to Gemini * refactor: removing unused if statement * fest: Add dummy model message for system message in gemini model * chore: update implementation --------- Co-authored-by: JustSong <[email protected]>
* fest: Add Google Gemini Pro, fix songquanpeng#810 * fest: Add tooling to Gemini; Add OpenAI-like system prompt to Gemini * refactor: removing unused if statement * fest: Add dummy model message for system message in gemini model * chore: update implementation --------- Co-authored-by: JustSong <[email protected]>
fix #810