[AGE-162] Add instrumentation for OpenAI

[mmabrouk]

We would like instrumentation for the OpenAI library. First we need to assess the different options. I see the following implementation patterns:

• Monkey patching (I think baserun do that)
• Providing another implementation (Langfuse and helicone do that)
• Providing a wrapper (Langsmith does that)

_{From SyncLinear.com | AGE-162}

[mmabrouk]

Solution used in Logfire:

import openai
import logfire

client = openai.Client()

logfire.instrument_openai(client)  

response = client.chat.completions.create(
    model='gpt-4',
    messages=[
        {'role': 'system', 'content': 'You are a helpful assistant.'},
        {'role': 'user', 'content': 'Please write me a limerick about Python logging.'},
    ],
)
print(response.choices[0].message)