Unresponsive chat when using remote self-hosted Ollama server about continue HOT 2 CLOSED

Sorry, I should have provided the whole config. Here it is, for reference.

{
  "models": [
    {
      "title": "Ollama",
      "provider": "ollama",
      "model": "mistral:latest",
      "apiBase": "http://192.168.1.123:11434",
      "completionOptions": {},
      "requestOptions": {
        "timeout": 1000
      }
    }
  ],
  "slashCommands": [
    {
      "name": "edit",
      "description": "Edit selected code"
    },
    {
      "name": "comment",
      "description": "Write comments for the selected code"
    },
    {
      "name": "share",
      "description": "Export this session as markdown"
    }
  ],
  "customCommands": [
    {
      "name": "test",
      "prompt": "Write a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don't edit any file.",
      "description": "Write unit tests for highlighted code"
    }
  ],
  "contextProviders": [
    {
      "name": "open",
      "params": {}
    }
  ]
}

This error modal popped up in VSCode after retying. Only the modal showed though, there weren't any errors in the Chrome console. I restarted VSCode and now it appears to be working.

I had toggled the apiBase between local Ollama (apiBase omitted from config) and remote Ollama ("apiBase": "http://192.168.1.123:11434",) many times, and I had also restarted VSCode on each change, so I don't know why it's working now all of the sudden.

Anyway, sorry for the noise. I wish I could provide better error logs.

from continue.

@MattyRad Are you entering literally 192.168.1.xxx:11434? It's important to keep URL scheme (http:// or https://).

Otherwise, if you could share the whole model object from your config, or any logs on the Continue side (cmd+shift+P, "Toggle Developer Tools") or the Ollama side, I can try to further debug. Many folks have used remote before so either there's some brand new regression or just a small blip in config (in which case we ought to improve the docs)

from continue.