I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.6.21
Ollama Version (if applicable)
No response
Operating System
ubuntu
Browser (if applicable)
chrome
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
The place where the title is generated should have a preset entry for the user to modify
Task: Generate a concise, 3-5 word title with an emoji summarizing the chat history. ### Guidelines: - The title should clearly represent the main theme or subject of the conversation. - Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting. - Write the title in the chat's primary language; default to English if multilingual. - Prioritize accuracy over excessive creativity; keep it clear and simple. - Your entire response must consist solely of the JSON object, without any introductory or concluding text. - The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text. - Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure. ### Output: JSON format: { "title": "your concise title here" } ### Examples: - { "title": "📉 Stock Market Trends" }, - { "title": "🍪 Perfect Chocolate Chip Recipe" }, - { "title": "Evolution of Music Streaming" }, - { "title": "Remote Work Productivity Tips" }, - { "title": "Artificial Intelligence in Healthcare" }, - { "title": "🎮 Video Game Development Insights" }
Steps to Reproduce
In the administrator console -> interface -> fill in the title to generate prompt words
Logs & Screenshots
Additional Information
No response
Originally created by @yuliang615 on GitHub (Aug 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16462
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.6.21
### Ollama Version (if applicable)
_No response_
### Operating System
ubuntu
### Browser (if applicable)
chrome
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
The place where the title is generated should have a preset entry for the user to modify
### Actual Behavior
改動標題生成的提示詞的時候 會有點像一整個核心功能被打鰾的感覺
具體情況是這樣 如果我在api log 那邊查看標題生成的紀錄 他會是搭配著前面的第一個對話 後面接上prompt
一但我修改prompt 之後 就會變成只有prompt 被提交出去
舉例
預設的prompt (沒填入任何文字)
user:二氧化碳是如何造成溫室效應的
GPT:二氧化碳會...導致...
標題:{ "title": "🌍 Carbon Dioxide Overview" }
經過修改後的prompt (即使只是填入原始prompt)
user:二氧化碳是如何造成溫室效應的
GPT:二氧化碳會...導致...
標題:{ "title": "📝 會話標題生成" }
提供原始prompt (open webui 定義的)
### Task: Generate a concise, 3-5 word title with an emoji summarizing the chat history. ### Guidelines: - The title should clearly represent the main theme or subject of the conversation. - Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting. - Write the title in the chat's primary language; default to English if multilingual. - Prioritize accuracy over excessive creativity; keep it clear and simple. - Your entire response must consist solely of the JSON object, without any introductory or concluding text. - The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text. - Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure. ### Output: JSON format: { "title": "your concise title here" } ### Examples: - { "title": "📉 Stock Market Trends" }, - { "title": "🍪 Perfect Chocolate Chip Recipe" }, - { "title": "Evolution of Music Streaming" }, - { "title": "Remote Work Productivity Tips" }, - { "title": "Artificial Intelligence in Healthcare" }, - { "title": "🎮 Video Game Development Insights" }
### Steps to Reproduce
In the administrator console -> interface -> fill in the title to generate prompt words
### Logs & Screenshots
<img width="2512" height="1597" alt="Image" src="https://github.com/user-attachments/assets/1ef842b7-cb49-4bd2-88f3-65b983adf768" />
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-25 07:21:51 -05:00
<!-- gh-comment-id:3173188241 -->
@cloudtuotuo commented on GitHub (Aug 11, 2025):
This part is missing at the end:
### Chat history
<chat_history>
{{MESSAGES:END:2}}
</chat_history>
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
I set the prompt like this:
You are a title generation expert. Please read the following text and create a short, topic-focused title (no more than 15 words):
<chat_history>
{{MESSAGES:END:2}}
</chat_history>
Only output the generated title. Do not repeat the original text or provide any commentary.
However the title is alway the first query of the user, is there anything wrong?
<!-- gh-comment-id:3802569454 -->
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
I set the prompt like this:
```
You are a title generation expert. Please read the following text and create a short, topic-focused title (no more than 15 words):
<chat_history>
{{MESSAGES:END:2}}
</chat_history>
Only output the generated title. Do not repeat the original text or provide any commentary.
```
However the title is alway the first query of the user, is there anything wrong?
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
The title will be generated if and only if the title prompt is empty (using default title prompt). Once I tried to use a customized title prompt, it won't work any more.
<!-- gh-comment-id:3802574511 -->
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
The title will be generated if and only if the title prompt is empty (using default title prompt). Once I tried to use a customized title prompt, it won't work any more.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @yuliang615 on GitHub (Aug 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16462
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.6.21
Ollama Version (if applicable)
No response
Operating System
ubuntu
Browser (if applicable)
chrome
Confirmation
README.md.Expected Behavior
The place where the title is generated should have a preset entry for the user to modify
Actual Behavior
改動標題生成的提示詞的時候 會有點像一整個核心功能被打鰾的感覺
具體情況是這樣 如果我在api log 那邊查看標題生成的紀錄 他會是搭配著前面的第一個對話 後面接上prompt
一但我修改prompt 之後 就會變成只有prompt 被提交出去
舉例
預設的prompt (沒填入任何文字)
user:二氧化碳是如何造成溫室效應的
GPT:二氧化碳會...導致...
標題:{ "title": "🌍 Carbon Dioxide Overview" }
經過修改後的prompt (即使只是填入原始prompt)
user:二氧化碳是如何造成溫室效應的
GPT:二氧化碳會...導致...
標題:{ "title": "📝 會話標題生成" }
提供原始prompt (open webui 定義的)
Task: Generate a concise, 3-5 word title with an emoji summarizing the chat history. ### Guidelines: - The title should clearly represent the main theme or subject of the conversation. - Use emojis that enhance understanding of the topic, but avoid quotation marks or special formatting. - Write the title in the chat's primary language; default to English if multilingual. - Prioritize accuracy over excessive creativity; keep it clear and simple. - Your entire response must consist solely of the JSON object, without any introductory or concluding text. - The output must be a single, raw JSON object, without any markdown code fences or other encapsulating text. - Ensure no conversational text, affirmations, or explanations precede or follow the raw JSON output, as this will cause direct parsing failure. ### Output: JSON format: { "title": "your concise title here" } ### Examples: - { "title": "📉 Stock Market Trends" }, - { "title": "🍪 Perfect Chocolate Chip Recipe" }, - { "title": "Evolution of Music Streaming" }, - { "title": "Remote Work Productivity Tips" }, - { "title": "Artificial Intelligence in Healthcare" }, - { "title": "🎮 Video Game Development Insights" }
Steps to Reproduce
In the administrator console -> interface -> fill in the title to generate prompt words
Logs & Screenshots
Additional Information
No response
@cloudtuotuo commented on GitHub (Aug 11, 2025):
This part is missing at the end:
Chat history
<chat_history>
{{MESSAGES:END:2}}
</chat_history>
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
I set the prompt like this:
However the title is alway the first query of the user, is there anything wrong?
@Steve-Li-1998 commented on GitHub (Jan 27, 2026):
The title will be generated if and only if the title prompt is empty (using default title prompt). Once I tried to use a customized title prompt, it won't work any more.