HTTP 404 Not Found from http://127.0.0.1:11434/api/generate This may mean that you forgot to add '/v1' to the end of your 'apiBase' in config.json.

[Barmaid1076]

Before submitting your bug report

• I believe this is a bug. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: windows
- Continue version: latest
- IDE version: latest
- Model: qwen2.5-coder:7b
- config.json:
  
{
  "models": [
    {
      "model": "AUTODETECT",
      "title": "Autodetect",
      "provider": "ollama"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Tab Autocomplete Model",
    "provider": "ollama",
    "model": "qwen2.5-coder:7b",
    "apiBase": "http://localhost:11434"
  },
  "tabAutocompleteOptions": {
    "debounceDelay": 500,
    "maxPromptTokens": 1500,
    "disableInFiles": [
      "*.md"
    ]
  }
}

Description

HTTP 404 Not Found from http://127.0.0.1:11434/api/generate This may mean that you forgot to add '/v1' to the end of your 'apiBase' in config.json.

I think it might be configuration not setup correctly，but i'm not sure what apiBase to use

To reproduce

No response

Log output

[Patrick-Erichsen]

Could you try this?

    "apiBase": "http://localhost:11434/v1"
`

[sarmbruster]

I think this error message can be misleading in some cases. I got the very same message when not having installed the referenced model.
Check with ollama list if qwen2.5-coder:7b is present. Ensure that it's type sensitive. I remember having install Qwen.... which also tiggered this message.

Ollama even sends a helpful message back in the http response but continue seems to convert it into a generic message.

[hieundx]

Seems like the 7b model is now named qwen2.5-coder:latest instead of qwen2.5-coder:7b according to OP. So just change that in Continue's config, it will work again.

ollama ps
NAME                    ID              SIZE      PROCESSOR    UNTIL              
qwen2.5-coder:latest    2b0496514337    6.0 GB    100% GPU     6 seconds from now   

[Barmaid1076]

Could you try this?

    "apiBase": "http://localhost:11434/v1"
`

Yes I have tried that but that's not what caused the problem, but still thank you for your help!

I think this error message can be misleading in some cases. I got the very same message when not having installed the referenced model. Check with ollama list if qwen2.5-coder:7b is present. Ensure that it's type sensitive. I remember having install Qwen.... which also tiggered this message.

Ollama even sends a helpful message back in the http response but continue seems to convert it into a generic message.

Yes it's the model name issue, thank you!

Seems like the 7b model is now named qwen2.5-coder:latest instead of qwen2.5-coder:7b according to OP. So just change that in Continue's config, it will work again.

Solved ! Thank you so much!