update

monitor_service.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""
+Monitor the Mistral Nemo service startup and run tests when ready.
+"""
+import time
+import requests
+import json
+import sys
+
+def check_service_health():
+    """Check if the service is healthy and ready."""
+    try:
+        response = requests.get("http://localhost:8001/health", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            return data.get("status") == "healthy"
+    except requests.exceptions.RequestException:
+        pass
+    return False
+
+def test_chat_completion():
+    """Test the chat completion endpoint."""
+    try:
+        response = requests.post(
+            "http://localhost:8001/v1/chat/completions",
+            headers={"Content-Type": "application/json"},
+            json={
+                "model": "unsloth/Mistral-Nemo-Instruct-2407",
+                "messages": [
+                    {"role": "user", "content": "Hello! Please say 'Service is working correctly' if you can read this."}
+                ],
+                "max_tokens": 50,
+                "temperature": 0.7
+            },
+            timeout=30
+        )
+        
+        if response.status_code == 200:
+            data = response.json()
+            content = data["choices"][0]["message"]["content"]
+            print(f"✅ Chat completion successful: {content}")
+            return True
+        else:
+            print(f"❌ Chat completion failed: {response.status_code} - {response.text}")
+            return False
+    except requests.exceptions.RequestException as e:
+        print(f"❌ Chat completion error: {e}")
+        return False
+
+def monitor_service():
+    """Monitor service startup and test when ready."""
+    print("🔍 Monitoring Mistral Nemo service startup...")
+    print("📥 Waiting for model download and loading to complete...")
+    
+    check_count = 0
+    max_checks = 300  # 25 minutes max wait
+    
+    while check_count < max_checks:
+        if check_service_health():
+            print("\n🎉 Service is healthy! Running tests...")
+            
+            # Test chat completion
+            if test_chat_completion():
+                print("\n✅ All tests passed! Mistral Nemo service is fully operational.")
+                return True
+            else:
+                print("\n⚠️ Service health check passed but chat completion failed.")
+                return False
+        
+        check_count += 1
+        dots = "." * (check_count % 4)
+        print(f"\r⏳ Waiting for service to be ready{dots:<3} ({check_count}/300)", end="")
+        time.sleep(5)
+    
+    print(f"\n❌ Service didn't become ready after {max_checks * 5} seconds")
+    return False
+
+if __name__ == "__main__":
+    success = monitor_service()
+    sys.exit(0 if success else 1)

test_mistral_service.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Test script for the Mistral Nemo Backend Service
+"""
+
+import requests
+import json
+import time
+
+# Service configuration
+BASE_URL = "http://localhost:8001"
+
+def test_health():
+    """Test the health endpoint"""
+    print("🏥 Testing health endpoint...")
+    try:
+        response = requests.get(f"{BASE_URL}/health", timeout=5)
+        if response.status_code == 200:
+            print(f"✅ Health check passed: {response.json()}")
+            return True
+        else:
+            print(f"❌ Health check failed: {response.status_code}")
+            return False
+    except Exception as e:
+        print(f"❌ Health check error: {e}")
+        return False
+
+def test_root():
+    """Test the root endpoint"""
+    print("🏠 Testing root endpoint...")
+    try:
+        response = requests.get(f"{BASE_URL}/", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ Root endpoint: {data}")
+            return True
+        else:
+            print(f"❌ Root endpoint failed: {response.status_code}")
+            return False
+    except Exception as e:
+        print(f"❌ Root endpoint error: {e}")
+        return False
+
+def test_models():
+    """Test the models endpoint"""
+    print("📋 Testing models endpoint...")
+    try:
+        response = requests.get(f"{BASE_URL}/v1/models", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ Available models: {[model['id'] for model in data['data']]}")
+            return True
+        else:
+            print(f"❌ Models endpoint failed: {response.status_code}")
+            return False
+    except Exception as e:
+        print(f"❌ Models endpoint error: {e}")
+        return False
+
+def test_chat_completion():
+    """Test a simple chat completion"""
+    print("💬 Testing chat completion...")
+    try:
+        payload = {
+            "model": "unsloth/Mistral-Nemo-Instruct-2407",
+            "messages": [
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": "Hello! Tell me a fun fact about AI."}
+            ],
+            "max_tokens": 100,
+            "temperature": 0.7
+        }
+        
+        response = requests.post(f"{BASE_URL}/v1/chat/completions", 
+                               json=payload, timeout=30)
+        
+        if response.status_code == 200:
+            data = response.json()
+            message = data["choices"][0]["message"]["content"]
+            print(f"✅ Chat completion successful!")
+            print(f"🤖 Assistant: {message}")
+            return True
+        else:
+            print(f"❌ Chat completion failed: {response.status_code}")
+            print(f"Response: {response.text}")
+            return False
+    except Exception as e:
+        print(f"❌ Chat completion error: {e}")
+        return False
+
+def wait_for_service():
+    """Wait for the service to be ready"""
+    print("⏳ Waiting for service to be ready...")
+    max_attempts = 60  # Wait up to 5 minutes
+    
+    for attempt in range(max_attempts):
+        try:
+            response = requests.get(f"{BASE_URL}/health", timeout=5)
+            if response.status_code == 200:
+                print(f"✅ Service is ready after {attempt * 5} seconds!")
+                return True
+        except:
+            pass
+        
+        if attempt < max_attempts - 1:
+            print(f"⏳ Attempt {attempt + 1}/{max_attempts} - waiting 5 seconds...")
+            time.sleep(5)
+    
+    print("❌ Service did not become ready within the timeout period")
+    return False
+
+def main():
+    """Run all tests"""
+    print("🚀 Testing Mistral Nemo Backend Service")
+    print("=" * 50)
+    
+    # Wait for service to be ready
+    if not wait_for_service():
+        print("❌ Service is not ready. Exiting.")
+        return
+    
+    # Run tests
+    tests = [test_root, test_health, test_models, test_chat_completion]
+    passed = 0
+    
+    for test in tests:
+        try:
+            if test():
+                passed += 1
+            print()
+        except Exception as e:
+            print(f"❌ Test failed with exception: {e}")
+            print()
+    
+    print("=" * 50)
+    print(f"📊 Test Results: {passed}/{len(tests)} tests passed")
+    
+    if passed == len(tests):
+        print("🎉 All tests passed! Your Mistral Nemo service is working perfectly!")
+    else:
+        print("⚠️ Some tests failed. Check the logs above for details.")
+
+if __name__ == "__main__":
+    main()