[Bug] 自定义模型支持图片输入，但选择自定义模型时默认无图片输入按钮 about chatgpt-next-web HOT 19 OPEN

我觉得最简单的办法是直接再增加一个配置项
直接由用户指定哪些模型支持图片,一劳永逸

from chatgpt-next-web.

你把模型名称修改为带vision的就有了

可是我是用的中转站如果在结尾加上vison就识别不到这个模型了欸

自己的中转站还是上游的，如果是自己部署的，类似oneapi、newapi那种，可以自己重定向一下模型名称

上游的，用的gpt4的中转站，商家自己定义了一个叫gpt4-all的模型可以接受图片输入与4turbo一致

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

Title: [Bug] Custom models support image input, but when selecting a custom model, there is no image input button by default.

from chatgpt-next-web.

你把模型名称修改为带vision的就有了

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

You can change the model name to include vision.

from chatgpt-next-web.

你把模型名称修改为带vision的就有了

可是我是用的中转站如果在结尾加上vison就识别不到这个模型了欸

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

You can change the model name to include vision.

But the transfer station I am using will not be able to recognize the model if vison is added at the end.

from chatgpt-next-web.

你把模型名称修改为带vision的就有了

可是我是用的中转站如果在结尾加上vison就识别不到这个模型了欸

自己的中转站还是上游的，如果是自己部署的，类似oneapi、newapi那种，可以自己重定向一下模型名称

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

You can change the model name to include vision.

But the transfer station I am using will not be able to recognize the model if vison is added at the end.

Your own transfer station is still upstream. If you deploy it yourself, like oneapi or newapi, you can redirect the model name yourself.

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

You can change the model name to include vision.

But the transfer station I am using will not be able to recognize the model if vison is added at the end.

Your own transfer station is still upstream. If you deploy it yourself, like oneapi or newapi, you can redirect the model name yourself.

Upstream, the transfer station using gpt4 is used. The merchant defines a model called gpt4-all, which can accept image input consistent with 4turbo.

from chatgpt-next-web.

那就只好改代码了，修改isVisionModel那个判断函数

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

Then we have to change the code and modify the isVisionModel judgment function

from chatgpt-next-web.

那就只好改代码了，修改isVisionModel那个判断函数

好吧，或者可以提个enhancement？可以选择是否是visionmodel

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

Then we have to change the code and modify the isVisionModel judgment function

Okay, maybe you can give me an enhancement? You can choose whether it is visionmodel

from chatgpt-next-web.

那就只好改代码了，修改isVisionModel那个判断函数

好吧，或者可以提个enhancement？可以选择是否是visionmodel

是的，已经有计划会在最新版本支持用户自由度更高的模型配置，目前，您可以在您的代码中，先修改 isVisionModel ，将需要支持图片上传能力的模型加入进去

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

Then we have to change the code and modify the isVisionModel judgment function

Okay, maybe you can give me an enhancement? You can choose whether it is visionmodel

Yes, there are plans to support model configuration with higher user freedom in the latest version. Currently, you can modify isVisionModel in your code first and add models that need to support image upload capabilities.

from chatgpt-next-web.

@Dean-YZG 如果新版没那么快的话，考虑到LLM目前发展的速度，是否可以先将isVisionModel always return true?
不然每次最新的模型出来，都得hard code模型名，再发版，把事情弄复杂了好像。（毕竟各家LLM名字没有一套约束，一些判断逻辑总是滞后的）

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

@Dean-YZG If the new version is not that fast, considering the current development speed of LLM, can isVisionModel always return true first?
Otherwise, every time the latest model comes out, we have to hard code the model name and then release it, which seems to complicate things. (After all, each LLM name does not have a set of constraints, and some judgment logic is always lagging behind)

from chatgpt-next-web.

Bot detected the issue body's language is not English, translate it automatically.

I think the easiest way is to directly add another configuration item
Directly let the user specify which models support images, once and for all

from chatgpt-next-web.