[GH-ISSUE #8317] v0.5.3 (latest) HTTP 405 attempting to connect to endpoint: [BASEURL]:3000/api/v1/chat/completions [BASEURL]:3000/api/chat/completions works #69684

Closed
opened 2026-05-13 01:59:15 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @nathan-curtis on GitHub (Jan 4, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8317

Bug Report

Important Notes

  • Before submitting a bug report: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.

  • Collaborate respectfully: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.

  • Contributing: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.

  • Bug reproducibility: If a bug cannot be reproduced with a :main or :dev Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!

Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!


Installation Method

Docker

Environment

  • Open WebUI Version: [e.g., v0.3.11]

  • Ollama (if applicable): [e.g., v0.2.0, v0.1.32-rc1]

  • Operating System: [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]

  • Browser (if applicable): [e.g., Chrome 100.0, Firefox 98.0]

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. (not available - postman recreation)
  • [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:

using CURL f to connect to completions endpoint [BASEURL]:3000/api/v1/chat/completions yields connection.

(This is hardcoded in the Homeassistant integration I'm using, and have tried two integrations that claim to be OpenAI 'compatible' both yield same issue - both appear to be attempting to connect to same endpoint

Actual Behavior:

v0.5.3 (latest) HTTP 405 attempting to connect to endpoint: [BASEURL]:3000/api/v1/chat/completions [BASEURL]:3000/api/chat/completions works (gives 200 OK and chat response)

Description

Bug Summary:
/api/chat/completions endpoint appears to work OK
/api/v1/chat/completions does not

(/api/v1/chat/completions is unfortunately the recognized endpoint in the other integration so it's bailing on error 405)

Reproduction Details

Steps to Reproduce:
[Outline the steps to reproduce the bug. Be as detailed as possible.]
Install openwebui
install valid openAI key
use OpenAI Key to connect to Homeasssistant integration directly. (verified works direct to cloud)
use openAI key to setup openwebUI, validate chat UI access works (It does)
Enable OpenWebui API access (toggle the new endpoint controls on and off to make sure they're all OFF - OPEN for good measure)
use homeassistant integration to point at OpenWebUI API
Fails - HTTP405

Pull server logs - find it's actually connecting to: [BASEURL]:3000/api/v1/chat/completions

Should it not be enabled by default if all access controls are off?
Should it not redirect api/v1/foo > api/foo and THEN access control?

Logs and Screenshots

Docker log from server console from simulations:
INFO: ('192.168.1.128', 51052) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket" [accepted]
INFO: connection open
DEBUG [open_webui.utils.middleware] form_data: {'model': 'gpt-4o-mini', 'messages': [{'role': 'user', 'content': 'this is a system connection test to API. please identify your purpose and model if known'}], 'metadata': {'user_id': '9d2eb0bb-20e0-44a8-ac3b-bcfc9fe99f5f', 'chat_id': None, 'message_id': None, 'session_id': None, 'tool_ids': None, 'files': None, 'features': None}}
DEBUG [open_webui.utils.middleware] tool_ids=None
INFO: 192.168.1.128:61980 - "POST /api/chat/completions HTTP/1.1" 200 OK
INFO: 192.168.1.128:52821 - "POST /api/v1/chat/completions HTTP/1.1" 405 Method Not Allowed
root@llama3:~/ollama-intel-gpu#

Docker log for actual service call attempt: (.12 is the HA server, .128 is my admin console running postman)
INFO: 192.168.1.12:57624 - "POST /api/v1/chat/completions HTTP/1.1" 405 Method Not Allowed
root@llama3:~/ollama-intel-gpu#

Additional Information

Extract from Intent trying to direct traffic to open-webui - note timestamp and response. (I cannot change its endpoint only base url and port)

HomeAssistant side:
init_options:
start_stage: intent
end_stage: intent
input:
text: Give me a test 05:03 local Jarvis
pipeline: 01jg7rpr2h4z9hg1p0rh7m38br
conversation_id: null
stage: done
run:
pipeline: 01jg7rpr2h4z9hg1p0rh7m38br
language: en
runner_data:
stt_binary_handler_id: null
timeout: 300
events:

  • type: run-start
    data:
    pipeline: 01jg7rpr2h4z9hg1p0rh7m38br
    language: en
    runner_data:
    stt_binary_handler_id: null
    timeout: 300
    timestamp: "2025-01-04T11:03:27.783479+00:00"
  • type: intent-start
    data:
    engine: 01JGR9KG6C4G0BA7Z4HDBWDRZX
    language: en
    intent_input: Give me a test 05:03 local Jarvis
    conversation_id: null
    device_id: null
    prefer_local_intents: false
    timestamp: "2025-01-04T11:03:27.783571+00:00"
  • type: intent-end
    data:
    processed_locally: false
    intent_output:
    response:
    speech:
    plain:
    speech: >-
    Sorry, I had a problem talking to OpenAI: Error code: 405 -
    {'detail': 'Method Not Allowed'}
    extra_data: null
    card: {}
    language: en
    response_type: error
    data:
    code: unknown
    conversation_id: 01JGRFQYSQ37SHSJ8F0P32R934
    timestamp: "2025-01-04T11:03:27.817044+00:00"
  • type: run-end
    data: null
    timestamp: "2025-01-04T11:03:27.817099+00:00"
    intent:
    engine: 01JGR9KG6C4G0BA7Z4HDBWDRZX
    language: en
    intent_input: Give me a test 05:03 local Jarvis
    conversation_id: null
    device_id: null
    prefer_local_intents: false
    done: true
    processed_locally: false
    intent_output:
    response:
    speech:
    plain:
    speech: >-
    Sorry, I had a problem talking to OpenAI: Error code: 405 -
    {'detail': 'Method Not Allowed'}
    extra_data: null
    card: {}
    language: en
    response_type: error
    data:
    code: unknown
    conversation_id: 01JGRFQYSQ37SHSJ8F0P32R934

Please review, this is blocking any user attempting to use open-webui (v.0.5.3 and below) between HomeAssistant and OpenAI (which is a heck of a use case)

Originally created by @nathan-curtis on GitHub (Jan 4, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8317 # Bug Report ## Important Notes - **Before submitting a bug report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project. - **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours. - **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI. - **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help! Note: Please remove the notes above when submitting your post. Thank you for your understanding and support! --- ## Installation Method Docker ## Environment - **Open WebUI Version:** [e.g., v0.3.11] - **Ollama (if applicable):** [e.g., v0.2.0, v0.1.32-rc1] - **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04] - **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0] **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. (not available - postman recreation) - [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: using CURL f to connect to completions endpoint [BASEURL]:3000/api/v1/chat/completions yields connection. (This is hardcoded in the Homeassistant integration I'm using, and have tried two integrations that claim to be OpenAI 'compatible' both yield same issue - both appear to be attempting to connect to same endpoint ## Actual Behavior: v0.5.3 (latest) HTTP 405 attempting to connect to endpoint: [BASEURL]:3000/api/v1/chat/completions [BASEURL]:3000/api/chat/completions works (gives 200 OK and chat response) ## Description **Bug Summary:** /api/chat/completions endpoint appears to work OK /api/v1/chat/completions does not (/api/v1/chat/completions is unfortunately the recognized endpoint in the other integration so it's bailing on error 405) ## Reproduction Details **Steps to Reproduce:** [Outline the steps to reproduce the bug. Be as detailed as possible.] Install openwebui install valid openAI key use OpenAI Key to connect to Homeasssistant integration directly. (verified works direct to cloud) use openAI key to setup openwebUI, validate chat UI access works (It does) Enable OpenWebui API access (toggle the new endpoint controls on and off to make sure they're all OFF - OPEN for good measure) use homeassistant integration to point at OpenWebUI API Fails - HTTP405 Pull server logs - find it's actually connecting to: [BASEURL]:3000/api/v1/chat/completions Should it not be enabled by default if all access controls are off? Should it not redirect api/v1/foo > api/foo and THEN access control? ## Logs and Screenshots Docker log from server console from simulations: INFO: ('192.168.1.128', 51052) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket" [accepted] INFO: connection open DEBUG [open_webui.utils.middleware] form_data: {'model': 'gpt-4o-mini', 'messages': [{'role': 'user', 'content': 'this is a system connection test to API. please identify your purpose and model if known'}], 'metadata': {'user_id': '9d2eb0bb-20e0-44a8-ac3b-bcfc9fe99f5f', 'chat_id': None, 'message_id': None, 'session_id': None, 'tool_ids': None, 'files': None, 'features': None}} DEBUG [open_webui.utils.middleware] tool_ids=None INFO: 192.168.1.128:61980 - "POST /api/chat/completions HTTP/1.1" 200 OK INFO: 192.168.1.128:52821 - "POST /api/v1/chat/completions HTTP/1.1" 405 Method Not Allowed root@llama3:~/ollama-intel-gpu# Docker log for actual service call attempt: (.12 is the HA server, .128 is my admin console running postman) INFO: 192.168.1.12:57624 - "POST /api/v1/chat/completions HTTP/1.1" 405 Method Not Allowed root@llama3:~/ollama-intel-gpu# ## Additional Information Extract from Intent trying to direct traffic to open-webui - note timestamp and response. (I cannot change its endpoint only base url and port) HomeAssistant side: init_options: start_stage: intent end_stage: intent input: text: Give me a test 05:03 local Jarvis pipeline: 01jg7rpr2h4z9hg1p0rh7m38br conversation_id: null stage: done run: pipeline: 01jg7rpr2h4z9hg1p0rh7m38br language: en runner_data: stt_binary_handler_id: null timeout: 300 events: - type: run-start data: pipeline: 01jg7rpr2h4z9hg1p0rh7m38br language: en runner_data: stt_binary_handler_id: null timeout: 300 timestamp: "2025-01-04T11:03:27.783479+00:00" - type: intent-start data: engine: 01JGR9KG6C4G0BA7Z4HDBWDRZX language: en intent_input: Give me a test 05:03 local Jarvis conversation_id: null device_id: null prefer_local_intents: false timestamp: "2025-01-04T11:03:27.783571+00:00" - type: intent-end data: processed_locally: false intent_output: response: speech: plain: speech: >- Sorry, I had a problem talking to OpenAI: Error code: 405 - {'detail': 'Method Not Allowed'} extra_data: null card: {} language: en response_type: error data: code: unknown conversation_id: 01JGRFQYSQ37SHSJ8F0P32R934 timestamp: "2025-01-04T11:03:27.817044+00:00" - type: run-end data: null timestamp: "2025-01-04T11:03:27.817099+00:00" intent: engine: 01JGR9KG6C4G0BA7Z4HDBWDRZX language: en intent_input: Give me a test 05:03 local Jarvis conversation_id: null device_id: null prefer_local_intents: false done: true processed_locally: false intent_output: response: speech: plain: speech: >- Sorry, I had a problem talking to OpenAI: Error code: 405 - {'detail': 'Method Not Allowed'} extra_data: null card: {} language: en response_type: error data: code: unknown conversation_id: 01JGRFQYSQ37SHSJ8F0P32R934 Please review, this is blocking any user attempting to use open-webui (v.0.5.3 and below) between HomeAssistant and OpenAI (which is a heck of a use case)
Author
Owner

@tjbck commented on GitHub (Jan 4, 2025):

api/v1/chat/completions was never an endpoint for Open WebUI.

<!-- gh-comment-id:2571262772 --> @tjbck commented on GitHub (Jan 4, 2025): `api/v1/chat/completions` was never an endpoint for Open WebUI.
Author
Owner

@nathan-curtis commented on GitHub (Jan 4, 2025):

api/v1/chat/completions was never an endpoint for Open WebUI.

Thx. I know how to handle it from there then

yay browser redirects...

Btw I'll bug both those projects and reference this.

<!-- gh-comment-id:2571263514 --> @nathan-curtis commented on GitHub (Jan 4, 2025): > `api/v1/chat/completions` was never an endpoint for Open WebUI. Thx. I know how to handle it from there then yay browser redirects... Btw I'll bug both those projects and reference this.
Author
Owner

@ZimaBlueee commented on GitHub (Apr 22, 2025):

api/v1/chat/completions was never an endpoint for Open WebUI.api/v1/chat/completions 从来都不是 Open WebUI 的端点。

Thx. I know how to handle it from there then谢谢。我知道该怎么处理了。

yay browser redirects...  耶,浏览器重定向……

Btw I'll bug both those projects and reference this.顺便说一句,我会对这两个项目进行检查并参考这一点。

@nathan-curtis I have the same problem, how did you solve it? Did you use nginx?

<!-- gh-comment-id:2820729849 --> @ZimaBlueee commented on GitHub (Apr 22, 2025): > > `api/v1/chat/completions` was never an endpoint for Open WebUI.`api/v1/chat/completions` 从来都不是 Open WebUI 的端点。 > > Thx. I know how to handle it from there then谢谢。我知道该怎么处理了。 > > yay browser redirects...  耶,浏览器重定向…… > > Btw I'll bug both those projects and reference this.顺便说一句,我会对这两个项目进行检查并参考这一点。 @nathan-curtis I have the same problem, how did you solve it? Did you use nginx?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#69684