Originally created by @starryloki on GitHub (Mar 31, 2024).
Bug Report
Description
Bug Summary:
I use one-api as a proxy aggregator for upstream APIs, which proxies OpenAI and Claude, and the downstream format of one-api is in OpenAI format. After accessing one-api through open-webui, I can use OpenAI normally but cannot use Claude. Although an error is prompted on open-webui, one-api has successfully requested Claude.
I once tried to use other tools to call Claude from one-api, and it was successful.
Actual Behavior:
External: {'message': 'messages.1.content.0.text.text: Field required (request id: 2024033123382364419163873473339)', 'type': 'invalid_request_error', 'param': '', 'code': None}
Environment
Debian 12 x86-64 6.1.0-18-amd64
Safari lastest
Open-WebUI docker lastest
Reproduction Details
Confirmation:
[Y] I have read and followed all the instructions provided in the README.md.
[Y] I am on the latest version of both Open WebUI and Ollama.
[Y] I have included the browser console logs.
[Y] I have included the Docker container logs.
Logs and Screenshots
Docker Container Logs:
INFO: 10.12.1.5:60299 - "POST /openai/api/chat/completions HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /api/v1/chats/0dc7fe26-517e-4aa0-a775-f9aff7693411 HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /openai/api/chat/completions HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /api/v1/chats/0dc7fe26-517e-4aa0-a775-f9aff7693411 HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
ERROR:apps.openai.main:400 Client Error: Bad Request for url: https://{API_ENDPOINT}/v1/chat/completions
Traceback (most recent call last):
File "/app/backend/apps/openai/main.py", line 325, in proxy
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://{API_ENDPOINT}/v1/chat/completions
INFO: 10.12.1.5:60300 - "POST /openai/api/chat/completions HTTP/1.1" 500 Internal Server Error
ERROR:apps.openai.main:529 Server Error: status code 529 for url: https://{API_ENDPOINT}/v1/chat/completions
Traceback (most recent call last):
File "/app/backend/apps/openai/main.py", line 325, in proxy
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 529 Server Error: status code 529 for url: https://{API_ENDPOINT}/v1/chat/completions
INFO: 10.12.1.5:60300 - "POST /openai/api/chat/completions HTTP/1.1" 500 Internal Server Error
The request with port number 60299 is a request for gpt3.5, the request was successful, and all subsequent ones are requests for claude.
Installation Method
docker
Originally created by @starryloki on GitHub (Mar 31, 2024).
# Bug Report
## Description
**Bug Summary:**
I use one-api as a proxy aggregator for upstream APIs, which proxies OpenAI and Claude, and the downstream format of one-api is in OpenAI format. After accessing one-api through open-webui, I can use OpenAI normally but cannot use Claude. Although an error is prompted on open-webui, one-api has successfully requested Claude.
I once tried to use other tools to call Claude from one-api, and it was successful.
**Actual Behavior:**
External: {'message': 'messages.1.content.0.text.text: Field required (request id: 2024033123382364419163873473339)', 'type': 'invalid_request_error', 'param': '', 'code': None}
## Environment
- Debian 12 x86-64 6.1.0-18-amd64
- Safari lastest
- Open-WebUI docker lastest
## Reproduction Details
**Confirmation:**
- [Y] I have read and followed all the instructions provided in the README.md.
- [Y] I am on the latest version of both Open WebUI and Ollama.
- [Y] I have included the browser console logs.
- [Y] I have included the Docker container logs.
## Logs and Screenshots
**Docker Container Logs:**
```
INFO: 10.12.1.5:60299 - "POST /openai/api/chat/completions HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /api/v1/chats/0dc7fe26-517e-4aa0-a775-f9aff7693411 HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /openai/api/chat/completions HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "POST /api/v1/chats/0dc7fe26-517e-4aa0-a775-f9aff7693411 HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
INFO: 10.12.1.5:60299 - "GET /api/v1/chats/ HTTP/1.1" 200 OK
ERROR:apps.openai.main:400 Client Error: Bad Request for url: https://{API_ENDPOINT}/v1/chat/completions
Traceback (most recent call last):
File "/app/backend/apps/openai/main.py", line 325, in proxy
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://{API_ENDPOINT}/v1/chat/completions
INFO: 10.12.1.5:60300 - "POST /openai/api/chat/completions HTTP/1.1" 500 Internal Server Error
ERROR:apps.openai.main:529 Server Error: status code 529 for url: https://{API_ENDPOINT}/v1/chat/completions
Traceback (most recent call last):
File "/app/backend/apps/openai/main.py", line 325, in proxy
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 529 Server Error: status code 529 for url: https://{API_ENDPOINT}/v1/chat/completions
INFO: 10.12.1.5:60300 - "POST /openai/api/chat/completions HTTP/1.1" 500 Internal Server Error
```
The request with port number 60299 is a request for gpt3.5, the request was successful, and all subsequent ones are requests for claude.
## Installation Method
docker
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 @starryloki on GitHub (Mar 31, 2024).
Bug Report
Description
Bug Summary:
I use one-api as a proxy aggregator for upstream APIs, which proxies OpenAI and Claude, and the downstream format of one-api is in OpenAI format. After accessing one-api through open-webui, I can use OpenAI normally but cannot use Claude. Although an error is prompted on open-webui, one-api has successfully requested Claude.
I once tried to use other tools to call Claude from one-api, and it was successful.
Actual Behavior:
External: {'message': 'messages.1.content.0.text.text: Field required (request id: 2024033123382364419163873473339)', 'type': 'invalid_request_error', 'param': '', 'code': None}
Environment
Reproduction Details
Confirmation:
Logs and Screenshots
Docker Container Logs:
The request with port number 60299 is a request for gpt3.5, the request was successful, and all subsequent ones are requests for claude.
Installation Method
docker