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:
Get a normal respond.
Actual Behavior:
Return Error 400.
Description
Bug Summary:
I received Error 400 when sending a message to a model from github marketplace, endpoint @ https://models.inference.ai.azure.com.
Reproduction Details
Steps to Reproduce:
pip install open-webui==0.3.21
open-webui serve
Go to Admin Panel - Settings - Connections.
Add https://models.inference.ai.azure.com as the API Endpoint under OpenAI API and Github token as the API Key.
Go back to "New Chat" and select "gpt-4o-mini".
Send a message.
Logs and Screenshots
Browser Console Logs:
Docker Container Logs:
N/A
Screenshots/Screen Recordings (if applicable):
Additional Information
Error Log:
ERROR [open_webui.apps.openai.main] 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
Traceback (most recent call last):
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/open_webui/apps/openai/main.py", line 414, in generate_chat_completion
r.raise_for_status()
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1093, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
INFO: 127.0.0.1:55136 - "POST /api/chat/completions HTTP/1.1" 400 Bad Request
INFO: 127.0.0.1:55136 - "POST /api/v1/chats/85371f10-1abb-4a9e-b8ab-a5f876c4183c HTTP/1.1" 200 OK
INFO: 127.0.0.1:55136 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
generate_title
azureml://registries/azure-openai/models/gpt-4o-mini/versions/1
ERROR [open_webui.apps.openai.main] 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
Traceback (most recent call last):
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/open_webui/apps/openai/main.py", line 414, in generate_chat_completion
r.raise_for_status()
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1093, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
INFO: 127.0.0.1:55136 - "POST /api/task/title/completions HTTP/1.1" 400 Bad Request
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
Originally created by @avcode-exe on GitHub (Sep 16, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/5457
# Bug Report
## Installation Method
`pip install open-webui`
## Environment
- **Open WebUI Version:** 0.3.21
- **Ollama (if applicable):** N/A
- **Operating System:** Windows 11 24H2 - WSL2 Ubuntu Preview
- **Browser (if applicable):** Arc 1.19.2 (49737) - Chromium Engine Version 128.0.6613.138
**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.
- [x] I have included the browser console logs.
- [ ] 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:
Get a normal respond.
## Actual Behavior:
Return Error 400.
## Description
**Bug Summary:**
I received Error 400 when sending a message to a model from github marketplace, endpoint @ `https://models.inference.ai.azure.com`.
## Reproduction Details
**Steps to Reproduce:**
1. `pip install open-webui==0.3.21`
2. `open-webui serve`
3. Go to Admin Panel - Settings - Connections.
4. Add `https://models.inference.ai.azure.com` as the API Endpoint under OpenAI API and Github token as the API Key.
5. Go back to "New Chat" and select "gpt-4o-mini".
6. Send a message.
## Logs and Screenshots
**Browser Console Logs:**
**Docker Container Logs:**
N/A
**Screenshots/Screen Recordings (if applicable):**
## Additional Information
**Error Log:**
```
ERROR [open_webui.apps.openai.main] 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
Traceback (most recent call last):
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/open_webui/apps/openai/main.py", line 414, in generate_chat_completion
r.raise_for_status()
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1093, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
INFO: 127.0.0.1:55136 - "POST /api/chat/completions HTTP/1.1" 400 Bad Request
INFO: 127.0.0.1:55136 - "POST /api/v1/chats/85371f10-1abb-4a9e-b8ab-a5f876c4183c HTTP/1.1" 200 OK
INFO: 127.0.0.1:55136 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
generate_title
azureml://registries/azure-openai/models/gpt-4o-mini/versions/1
ERROR [open_webui.apps.openai.main] 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
Traceback (most recent call last):
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/open_webui/apps/openai/main.py", line 414, in generate_chat_completion
r.raise_for_status()
File "/home/alphabeta/miniconda3/envs/Open-WebUI-py311/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1093, in raise_for_status
raise ClientResponseError(
aiohttp.client_exceptions.ClientResponseError: 400, message='Bad Request', url='https://models.inference.ai.azure.com/chat/completions'
INFO: 127.0.0.1:55136 - "POST /api/task/title/completions HTTP/1.1" 400 Bad Request
```
## Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
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 @avcode-exe on GitHub (Sep 16, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/5457
Bug Report
Installation Method
pip install open-webuiEnvironment
Open WebUI Version: 0.3.21
Ollama (if applicable): N/A
Operating System: Windows 11 24H2 - WSL2 Ubuntu Preview
Browser (if applicable): Arc 1.19.2 (49737) - Chromium Engine Version 128.0.6613.138
Confirmation:
Expected Behavior:
Get a normal respond.
Actual Behavior:
Return Error 400.
Description
Bug Summary:
I received Error 400 when sending a message to a model from github marketplace, endpoint @
https://models.inference.ai.azure.com.Reproduction Details
Steps to Reproduce:
pip install open-webui==0.3.21open-webui servehttps://models.inference.ai.azure.comas the API Endpoint under OpenAI API and Github token as the API Key.Logs and Screenshots
Browser Console Logs:
Docker Container Logs:
N/A
Screenshots/Screen Recordings (if applicable):
Additional Information
Error Log:
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!