There was an error processing your request: An error occurred.

[Soumyaranjan-17]

Describe the bug

I have ollama and also have qwen2.5-coder:14b model
I have made a file name modelFile

Q1: why it is requesting localhost:1234/v1/models

Ollama is running on its default port

FROM qwen2.5-coder:14b
PARAMETER num_ctx 32768

After starting the server and a chat, it shows the error
There was an error processing your request: An error occurred.

Link to the Bolt URL that caused the error

http://localhost:3000/chat/8

Steps to reproduce

1. start the server
2. start a chat

Expected behavior

This will show a error like this

Screen Recording / Screenshot

Here I found the port 1234

async function getLMStudioModels(_apiKeys?: Record<string, string>, settings?: IProviderSetting): Promise<ModelInfo[]> {
  try {
    const baseUrl = settings?.baseUrl || import.meta.env.LMSTUDIO_API_BASE_URL || 'http://localhost:1234';
    const response = await fetch(`${baseUrl}/v1/models`);
    const data = (await response.json()) as any;

    return data.data.map((model: any) => ({
      name: model.id,
      label: model.id,
      provider: 'LMStudio',
    }));
  } catch (e: any) {
    logStore.logError('Failed to get LMStudio models', e, { baseUrl: settings?.baseUrl });
    return [];
  }
}

if we can fix this ?

Platform

• OS: [e.g. Window11]
• Browser: [Edge, Chrome]
• Version: [ Latest ]

Provider Used

No response

Model Used

No response

Additional context

No response