#!/usr/bin/env python3 """ Test script for Ollama OpenELM API """ from openai import OpenClient def test_ollama(): """Test Ollama with OpenAI SDK.""" print("Testing Ollama OpenELM with OpenAI SDK...") print("-" * 50) client = OpenAI( base_url="http://127.0.0.1:11434/v1", api_key="ollama", ) # Test 1: Basic generation print("\n[Test 1] Basic generation:") response = client.chat.completions.create( model="apple/OpenELM-3B-Instruct", messages=[{"role": "user", "content": "Say hello!"}], max_tokens=100, temperature=0.7 ) print(f"Response: {response.choices[0].message.content}") print(f"Tokens: {response.usage.total_tokens}") # Test 2: Multi-turn conversation print("\n[Test 2] Multi-turn conversation:") response = client.chat.completions.create( model="apple/OpenELM-3B-Instruct", messages=[ {"role": "user", "content": "What is AI?"}, {"role": "assistant", "content": "AI is Artificial Intelligence."}, {"role": "user", "content": "What are examples?"} ], max_tokens=150, temperature=0.5 ) print(f"Response: {response.choices[0].message.content}") # Test 3: Creative writing print("\n[Test 3] Creative writing:") response = client.chat.completions.create( model="apple/OpenELM-3B-Instruct", messages=[{"role": "user", "content": "Write a short poem about technology."}], max_tokens=200, temperature=0.8 ) print(f"Response: {response.choices[0].message.content}") # Test 4: Question answering print("\n[Test 4] Question answering:") response = client.chat.completions.create( model="apple/OpenELM-3B-Instruct", messages=[{"role": "user", "content": "Explain what is machine learning in simple terms."}], max_tokens=250, temperature=0.6 ) print(f"Response: {response.choices[0].message.content}") print("\n" + "=" * 50) print("All tests completed successfully!") print("=" * 50) if __name__ == "__main__": test_ollama()