llm_council/scripts/test_ollama_direct.py

#!/usr/bin/env python3
"""Test direct connection to Ollama on GPU VM."""
import asyncio
import httpx

async def test():
    base = "http://10.0.30.63:11434"
    urls = [
        f"{base}/v1/models",
        f"{base}/api/tags",
    ]
    
    for url in urls:
        print(f"\nTesting: {url}")
        try:
            async with httpx.AsyncClient(timeout=5.0) as client:
                resp = await client.get(url)
                print(f"  Status: {resp.status_code}")
                if resp.status_code == 200:
                    data = resp.json()
                    print(f"  Keys: {list(data.keys())}")
                    if 'models' in data:
                        models = [m.get('name', m.get('model', m)) for m in data['models']]
                        print(f"  Found {len(models)} models: {models}")
                    elif 'data' in data:
                        models = [m.get('id', m) for m in data['data']]
                        print(f"  Found {len(models)} models: {models}")
        except httpx.TimeoutException:
            print(f"  ✗ Timeout - Ollama may only be listening on localhost")
        except Exception as e:
            print(f"  ✗ Error: {e}")

asyncio.run(test())