RUN.py

from openai import OpenAI

# Set up the client
client = OpenAI(
    base_url="http://localhost:8000/v1",  # Update this if you're not running locally
    api_key="C0TNRcI8EuhmXpRTNiNsGbUHWBG6KFQt"  # This can be any string as we're not actually validating it
)

def test_non_streaming():
    print("Testing non-streaming response:")
    completion = client.chat.completions.create(
        model="claude-3.5-sonnet",
        messages=[
            {"role": "system", "content": "."},
            {"role": "user", "content": "how many 'r' are there in strawberry"}
        ]
    )
    print(completion)
    # print(completion.choices[0].message.content)

def test_streaming():
    print("\nTesting streaming response:")
    completion = client.chat.completions.create(
        model="o1-preview",
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "how many 'r' are there in strawberry"}
        ],
        stream=True
    )
    for chunk in completion:
        # print(chunk)
        if chunk.choices[0].delta.content is not None:
            print(chunk.choices[0].delta.content, end="", flush=True)
    print()

if __name__ == "__main__":
    test_non_streaming()
    print("-"*50)
    test_streaming()