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

[Feature Request] 当前对话设置中[预设提示词]列表可以使用JSON导入 #6029

Open
KangSpace opened this issue Jan 4, 2025 · 1 comment
Labels
enhancement New feature or request

Comments

@KangSpace
Copy link

🥰 Feature Description

image
如图:
应用场景:

  1. 调试带对话上下文提示词的场景下,输入对话历史的情况
    可以使用JSON自动导入messages

🧐 Proposed Solution

  1. 将JSON可以导入为消息列表
    JSON格式(同输入模型的messages格式)如下:
[
{
"role":"system",
"content":"我是系统提示词"
},
{
"role":"user",
"content":"你是谁"
},
{
"role":"assistant",
"content":"我是人工智能助手"
}
]

将转换的内容,添加到预设提示词的为止,并且2者(JSON和对话数据)互相同步
image

📝 Additional Information

No response

@KangSpace KangSpace added the enhancement New feature or request label Jan 4, 2025
@Issues-translate-bot
Copy link

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


Title: [Feature Request] The [default prompt words] list in the current conversation settings can be imported using JSON

🥰 Feature Description

image
As shown in the picture:
Application scenarios:

  1. Debugging the situation of inputting dialogue history in a scenario with dialogue context prompt words
    Messages can be automatically imported using JSON

🧐 Proposed Solution

  1. Import JSON as a message list
    The JSON format (same as the messages format of the input model) is as follows:
[
{
"role":"system",
"content":"I am the system prompt word"
},
{
"role":"user",
"content":"Who are you"
},
{
"role":"assistant",
"content":"I am an artificial intelligence assistant"
}
]

Add the converted content to the preset prompt words, and the two (JSON and conversation data) are synchronized with each other.
image

📝 Additional Information

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants