lobehub
[Bug] 自动创建话题功能全部是默认话题了
💻 Operating System
Windows
📦 Environment
Official Preview
🌐 Browser
Chrome
🐛 Bug Description
🚦 Expected Behavior
No response
📷 Recurrence Steps
No response
📝 Additional Information
No response
👀 @a616824431
Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
This happened a long time ago. Did no one notice it?
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Have you turned it off in settings? You can set in the settings whether to automatically create topics.
默认使用的是openai 的gpt-3.5 模型来的话题标题总结，如果你不添加openai 的apikey，就没法正常总结。其他用openai 的人不会遇到这个问题，可能你用的不是openai 的吧。
后续我们会做个改造，支持选择固定模型/当前会话模型进行总结，或者禁用自动总结
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
By default, the topic title summary based on openai's gpt-3.5 model is used. If you do not add openai's apikey, you will not be able to summarize normally. Other people who use openai will not encounter this problem. Maybe you are not using openai.
We will make a modification in the future to support selecting fixed model/current session model for summary, or disable automatic summary.
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
Now I know what's going on. The key I used does not have a channel for the gpt-3.5 model. There are only some channels related to gpt4
默认使用的是openai 的gpt-3.5 模型来的话题标题总结，如果你不添加openai 的apikey，就没法正常总结。其他用openai 的人不会遇到这个问题，可能你用的不是openai 的吧。
后续我们会做个改造，支持选择固定模型/当前会话模型进行总结，或者禁用自动总结
建议加个可选：不支持话题总结的话，可以摘录首个聊天的前 x 个字符作为话题标题
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
By default, the topic title summary based on openai's gpt-3.5 model is used. If you do not add openai's apikey, you will not be able to summarize normally. Other people who use openai will not encounter this problem. Maybe you are not using openai.
In the future, we will make a modification to support selecting fixed model/current session model for summary, or disable automatic summary.
It is recommended to add an optional: If topic summary is not supported, you can excerpt the first x characters of the first chat as the topic title
默认使用的是openai 的gpt-3.5 模型来的话题标题总结，如果你不添加openai 的apikey，就没法正常总结。其他用openai 的人不会遇到这个问题，可能你用的不是openai 的吧。 后续我们会做个改造，支持选择固定模型/当前会话模型进行总结，或者禁用自动总结
建议加个可选：不支持话题总结的话，可以摘录首个聊天的前 x 个字符作为话题标题
为什么不能是用当前正在使用的模型进行标题总结呢？
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
By default, openai's gpt-3.5 model is used to summarize topic titles. If you do not add openai's apikey, you will not be able to summarize normally. Other people who use openai will not encounter this problem. Maybe you are not using openai. We will make a modification in the future to support selecting fixed model/current session model for summary, or disable automatic summary.
It is recommended to add an optional: If topic summary is not supported, you can excerpt the first x characters of the first chat as the topic title
Why can't we use the model currently being used for title summary?
默认使用的是openai 的gpt-3.5 模型来的话题标题总结，如果你不添加openai 的apikey，就没法正常总结。其他用openai 的人不会遇到这个问题，可能你用的不是openai 的吧。 后续我们会做个改造，支持选择固定模型/当前会话模型进行总结，或者禁用自动总结
建议加个可选：不支持话题总结的话，可以摘录首个聊天的前 x 个字符作为话题标题
为什么不能是用当前正在使用的模型进行标题总结呢？
我想到的是，如果话题总结+当前咨询问题是一次请求的话，用模型总结是比较好的，但是如果“话题总结”跟“当前咨询问题”是分开请求的话，会比较消耗token，特别是比较长的聊天
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
By default, openai's gpt-3.5 model is used to summarize topic titles. If you do not add openai's apikey, you will not be able to summarize normally. Other people who use openai will not encounter this problem. Maybe you are not using openai. We will make a modification in the future to support selecting fixed model/current session model for summary, or disable automatic summary.
It is recommended to add an optional: If topic summary is not supported, you can excerpt the first x characters of the first chat as the topic title
Why can't we use the model currently being used to summarize the title?
What I think of is that if the topic summary + the current consultation question are one request, it is better to use the model summary, but if the "topic summary" and the "current consultation question" are requested separately, it will consume more tokens, especially when comparing long chat
Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑🤝🧑👫🧑🏿🤝🧑🏻👩🏾🤝👨🏿👬🏿
You can just summarize the questions.
✅ @a616824431
This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。
:tada: This issue has been resolved in version 0.162.0 :tada:
The release is available on:
Your semantic-release bot :package::rocket:
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}