ChatGPTNextWeb/NextChat

[Feature Request] Support Gemini nano

Open

#5220 opened on Aug 7, 2024

View on GitHub
 (2 comments) (0 reactions) (1 assignee)TypeScript (87,992 stars) (59,717 forks)batch import
enhancementhelp wantedplanned

Description

🥰 Feature Description

Support Gemini nano

https://developer.chrome.com/docs/ai/built-in

🧐 Proposed Solution

  1. 先判断gemini nano在设备上可用的时候，把模型加到all models列表里面
  2. 在client/platform/google里面针对gemini nano特殊处理一下，调用本地模型就可以了

📝 Additional Information

No response

Contributor guide

Tech stack
typescriptreactnextjs
Domain
frontend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Familiarity with Next.js codebaseBasic understanding of Gemini nanoExperience with TypeScript
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Investigate the existing model loading mechanism in the codebase, particularly the all models list. Check the 'client/platform/google' directory for current Google provider implementation. Review any comments in the issue or related files to understand how to detect Gemini nano availability via the Chrome built in AI API. Then implement the two proposed steps: add the model to the list when available and handle the special case in the Google platform client.