ChatGPTNextWeb/NextChat

[Feature Request] 更灵活的视觉模型判别

Open

#5843 opened on Nov 18, 2024

View on GitHub
 (4 comments) (1 reaction) (0 assignees)TypeScript (87,992 stars) (59,717 forks)batch import
enhancementgood first issuehelp wanted

Description

🥰 需求描述

当前项目采用固定的关键词、排除关键词的方案进行视觉模型判别（isVisionModel），加上各模型厂商并没有采取一致的命名方案，导致模型视觉判别滞后和频繁修改，如最新的 gemini-exp-1114 也支持视觉能力了，但是当前的视觉判别不能直接适配，急需优化更灵活的视觉模型判别方法

🧐 解决方案

可能的解决方案：

  1. 允许通过环境变量给指定的模型加上视觉能力，如: VisionModel=model_1,model_2,model_3
  2. 允许前端网页配置、后台解析支持视觉能力的模型
  3. ...

📝 补充信息

No response

Contributor guide

Tech stack
typescriptreactnodejs
Domain
backendfull stack
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.
needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Understand current isVisionModel implementationFamiliarity with environment variable configuration in NextChat
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50
Research direction
Investigate the current isVisionModel function in the codebase (likely in src/utils/model.ts) to understand how vision capability is determined. Then design a flexible mechanism such as an environment variable (e.g., VISION MODELS) or a frontend configuration that allows users to define which models have vision support. Consider how to parse and apply such configuration across the application. Review existing environment variable patterns in the project (e.g., CUSTOM MODELS) for consistency.