[GH-ISSUE #8048] API Endpoint /api/chat/completions not work working #14977

New Issue

2026-04-19T21:12:46-05:00

GiteaMirror commented

2026-04-19 21:12:46 -05:00

Originally created by @mbeltagy on GitHub (Dec 25, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8048

Installation Method

Open WebUI and Ollama on two separate Docker containers

Environment

Open WebUI Version: [v0.4.8]
Ollama : [v0.5.4]
Operating System: [ Ubuntu 22.04]

Confirmation:

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 Docker container logs.
I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Expected Behavior:

Calling the endpoint with api key and prompt should result in a response.

Actual Behavior:

curl -X POST  http://localhost:3000/chat/completions \
-H "Authorization: Bearer sk-cafafdadfaf454734b" \
-H "Content-Type: application/json" \
-d '{
      "model": "llama3.2:latest",
      "messages": [
        {
          "role": "user",
          "content": "Why is the sky blue?"
        }
      ]
    }'

response
{"detail":"Method Not Allowed"}

Description

Bug Summary:
[Provide a brief but clear summary of the bug]

Reproduction Details

Steps to Reproduce:
[Outline the steps to reproduce the bug. Be as detailed as possible.]

Logs and Screenshots

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:
[Include relevant Docker container logs, if applicable]

Screenshots/Screen Recordings (if applicable):
[Attach any relevant screenshots to help illustrate the issue]

Additional Information

Open WebUI logs

INFO  [open_webui.apps.openai.main] get_all_models()
INFO  [open_webui.apps.ollama.main] get_all_models()
INFO:     172.17.0.1:42600 - "POST /chat/completions HTTP/1.1" 405 Method Not Allowed

$ ollama ls
NAME                      ID              SIZE      MODIFIED    
qwen2.5:7b                845dbda0ea48    4.7 GB    2 weeks ago    
llama3.3:latest           a6eb4748fd29    42 GB     2 weeks ago    
llama3.2-vision:latest    38107a0cd119    7.9 GB    3 weeks ago    
qwen2.5-coder:32b         4bd6cbf2d094    19 GB     4 weeks ago    
qwen2.5-coder:14b         3028237cc8c5    9.0 GB    4 weeks ago    
qwen2.5-coder:7b          2b0496514337    4.7 GB    4 weeks ago    
llama3.1:70b              c0df3564cfe8    39 GB     4 weeks ago    
llama3.1:latest           42182419e950    4.7 GB    4 weeks ago    
llama3.2:latest           a80c4f17acd5    2.0 GB    4 weeks ago    
llama3:latest             365c0bd3c000    4.7 GB    4 weeks ago

I get the same error on all of the above models.

Originally created by @mbeltagy on GitHub (Dec 25, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/8048 ## Installation Method Open WebUI and Ollama on two separate Docker containers ## Environment - **Open WebUI Version:** [v0.4.8] - **Ollama :** [v0.5.4] - **Operating System:** [ Ubuntu 22.04] **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 Docker container logs. - [x] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Expected Behavior: Calling the endpoint with api key and prompt should result in a response. ## Actual Behavior: ``` curl -X POST http://localhost:3000/chat/completions \ -H "Authorization: Bearer sk-cafafdadfaf454734b" \ -H "Content-Type: application/json" \ -d '{ "model": "llama3.2:latest", "messages": [ { "role": "user", "content": "Why is the sky blue?" } ] }' ``` response `{"detail":"Method Not Allowed"}` ## Description **Bug Summary:** [Provide a brief but clear summary of the bug] ## Reproduction Details **Steps to Reproduce:** [Outline the steps to reproduce the bug. Be as detailed as possible.] ## Logs and Screenshots **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** [Include relevant Docker container logs, if applicable] **Screenshots/Screen Recordings (if applicable):** [Attach any relevant screenshots to help illustrate the issue] ## Additional Information Open WebUI logs ``` INFO [open_webui.apps.openai.main] get_all_models() INFO [open_webui.apps.ollama.main] get_all_models() INFO: 172.17.0.1:42600 - "POST /chat/completions HTTP/1.1" 405 Method Not Allowed ``` ``` $ ollama ls NAME ID SIZE MODIFIED qwen2.5:7b 845dbda0ea48 4.7 GB 2 weeks ago llama3.3:latest a6eb4748fd29 42 GB 2 weeks ago llama3.2-vision:latest 38107a0cd119 7.9 GB 3 weeks ago qwen2.5-coder:32b 4bd6cbf2d094 19 GB 4 weeks ago qwen2.5-coder:14b 3028237cc8c5 9.0 GB 4 weeks ago qwen2.5-coder:7b 2b0496514337 4.7 GB 4 weeks ago llama3.1:70b c0df3564cfe8 39 GB 4 weeks ago llama3.1:latest 42182419e950 4.7 GB 4 weeks ago llama3.2:latest a80c4f17acd5 2.0 GB 4 weeks ago llama3:latest 365c0bd3c000 4.7 GB 4 weeks ago ``` I get the same error on all of the above models.

GiteaMirror closed this issue

2026-04-19 21:12:46 -05:00

GiteaMirror referenced this issue

2026-04-19 23:10:56 -05:00

[GH-ISSUE #14977] feat: How to set the maximum context length in a single session （设置单次会话中的最大上下文长度或者设置历史对话轮次的最大数量） #17429

GiteaMirror referenced this issue

2026-04-25 06:47:43 -05:00

[GH-ISSUE #14977] feat: How to set the maximum context length in a single session （设置单次会话中的最大上下文长度或者设置历史对话轮次的最大数量） #32958

GiteaMirror referenced this issue

2026-05-05 18:40:37 -05:00

[GH-ISSUE #14977] feat: How to set the maximum context length in a single session （设置单次会话中的最大上下文长度或者设置历史对话轮次的最大数量） #56095

GiteaMirror referenced this issue