I have read and followed all the instructions provided in the README.md.
I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
Expected Behavior:
When asking an LMM something, OpenWeb UI should autogenerate the title for the chat
Actual Behavior:
The title is not autogenerated and the chat stays on "New Chat"
Reproduction Details
Steps to Reproduce:
Ask the LMM something
The LMM will answer but the chat's title won't be generated
Logs and Screenshots
Browser Console Logs:
No errors
Docker Container Logs:
Spotted the following error:
ERROR [open_webui.routers.openai] 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
Traceback (most recent call last):
File "/app/backend/open_webui/routers/openai.py", line 679, in generate_chat_completion
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1157, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
ERROR [open_webui.routers.tasks] Exception occurred
Traceback (most recent call last):
File "/app/backend/open_webui/routers/openai.py", line 679, in generate_chat_completion
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1157, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/tasks.py", line 187, in generate_title
return await generate_chat_completion(request, form_data=payload, user=user)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/utils/chat.py", line 155, in generate_chat_completion
return await generate_openai_chat_completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/openai.py", line 691, in generate_chat_completion
raise HTTPException(
fastapi.exceptions.HTTPException: 400: Setting 'max_tokens' and 'max_completion_tokens' at the same time is not supported.
Originally created by @Simi5599 on GitHub (Dec 25, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8075
# Bug Report
## Installation Method
Docker
## Environment
- **Open WebUI Version:** 0.5.0
**Confirmation:**
- [x] I have read and followed all the instructions provided in the README.md.
- [x] I am on the latest version of both Open WebUI and Ollama.
- [ ] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
## Expected Behavior:
When asking an LMM something, OpenWeb UI should autogenerate the title for the chat
## Actual Behavior:
The title is not autogenerated and the chat stays on "New Chat"
## Reproduction Details
**Steps to Reproduce:**
1. Ask the LMM something
2. The LMM will answer but the chat's title won't be generated
## Logs and Screenshots
**Browser Console Logs:**
No errors
**Docker Container Logs:**
Spotted the following error:
```
ERROR [open_webui.routers.openai] 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
Traceback (most recent call last):
File "/app/backend/open_webui/routers/openai.py", line 679, in generate_chat_completion
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1157, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
ERROR [open_webui.routers.tasks] Exception occurred
Traceback (most recent call last):
File "/app/backend/open_webui/routers/openai.py", line 679, in generate_chat_completion
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1157, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://api.openai.com/v1/chat/completions'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/tasks.py", line 187, in generate_title
return await generate_chat_completion(request, form_data=payload, user=user)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/utils/chat.py", line 155, in generate_chat_completion
return await generate_openai_chat_completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/openai.py", line 691, in generate_chat_completion
raise HTTPException(
fastapi.exceptions.HTTPException: 400: Setting 'max_tokens' and 'max_completion_tokens' at the same time is not supported.
```
Wonderful, i was just about making a PR with the same fix you did!
I will copy your code and test it on my environment in 20 min!
<!-- gh-comment-id:2562026458 -->
@Simi5599 commented on GitHub (Dec 25, 2024):
Wonderful, i was just about making a PR with the same fix you did!
I will copy your code and test it on my environment in 20 min!
Can confirm this is working on my side! (OpenAI APIs)
<!-- gh-comment-id:2562031336 -->
@Simi5599 commented on GitHub (Dec 26, 2024):
Can confirm this is working on my side! (OpenAI APIs)
This condition controls title/tags generation tasks, but fails when you have a user-level system prompt configured in settings - new chats start with 2 messages [system, user] instead of 1, so generation never triggers.
<!-- gh-comment-id:2562193422 -->
@msurma commented on GitHub (Dec 26, 2024):
Hit the same issue. Found the cause in chat request logic:
https://github.com/open-webui/open-webui/blame/23bf71022e7d6401b8b84f2f1aa16e148eb120d6/src/lib/components/chat/Chat.svelte#L1508
This condition controls title/tags generation tasks, but fails when you have a user-level system prompt configured in settings - new chats start with 2 messages [system, user] instead of 1, so generation never triggers.
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 @Simi5599 on GitHub (Dec 25, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8075
Bug Report
Installation Method
Docker
Environment
Confirmation:
Expected Behavior:
When asking an LMM something, OpenWeb UI should autogenerate the title for the chat
Actual Behavior:
The title is not autogenerated and the chat stays on "New Chat"
Reproduction Details
Steps to Reproduce:
Logs and Screenshots
Browser Console Logs:
No errors
Docker Container Logs:
Spotted the following error:
@tjbck commented on GitHub (Dec 25, 2024):
Fixed on dev! Testing wanted here!
@Simi5599 commented on GitHub (Dec 25, 2024):
Wonderful, i was just about making a PR with the same fix you did!
I will copy your code and test it on my environment in 20 min!
@Simi5599 commented on GitHub (Dec 26, 2024):
Can confirm this is working on my side! (OpenAI APIs)
@msurma commented on GitHub (Dec 26, 2024):
Hit the same issue. Found the cause in chat request logic:
https://github.com/open-webui/open-webui/blame/23bf71022e7d6401b8b84f2f1aa16e148eb120d6/src/lib/components/chat/Chat.svelte#L1508
This condition controls title/tags generation tasks, but fails when you have a user-level system prompt configured in settings - new chats start with 2 messages [system, user] instead of 1, so generation never triggers.