MacOS 404 reply with Ollama

[vdddslep]

Goose v1.0.4

% cat ~/.config/goose/config.yaml
OLLAMA_HOST: http://localhost:11434/
GOOSE_PROVIDER: ollama
GOOSE_MODEL: qwen2.5

[vdddslep]

same result

[salman1993]

Can you confirm that your Ollama server is running? You might need to open another terminal window and run: ollama serve

then verify Ollama is able to serve requests:

  curl http://localhost:11434/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "qwen2.5", # REPALCE WITH YOUR MODEL
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Hello!"
            }
        ]
    }'

if the curl requests work, then Goose should be able to use the Ollama model

[vdddslep]

its running and it works, Im using it in open web UI

Also as far as I remember --->> curl http://localhost:11434/v1/chat/completions ->> v1 its OpenAI-Like format

[salman1993]

that's expected - we're using Ollama's Open AI compatible endpoint.

if you're using the Goose GUI, can you try resetting the provider and trying to chat?

i am not able to replicate the error you're seeing. goose configure succeeds for me.

[vdddslep]

I've figured out!
I put the model name as qwen2.5:7b, and it let me save it, and now everything works!!
Before, when I tried to save the model name as qwen2.5:7b, it saved as qwen2.5 instead. I'm sure I tried this a few times

Any way thank you for your help