feat(instrumentation): new spans for llms

[RogerHYang]

Before

After

Code

def multiply(a: int, b: int) -> int:
    """Multiple two integers and returns the result integer"""
    return a * b


def add(a: int, b: int) -> int:
    """Add two integers and returns the result integer"""
    return a + b


multiply_tool = FunctionTool.from_defaults(fn=multiply)
add_tool = FunctionTool.from_defaults(fn=add)
agent = OpenAIAgent.from_tools([multiply_tool, add_tool])
Settings.llm = OpenAI(model="gpt-3.5-turbo")

if __name__ == "__main__":
    response = agent.query("What is (121 * 3) + 42?")
    print(response)

[nerdai]

Ohhhh this is nice!

Up to now, I've been resorting to decorating the subclasses individually. If I'm reading this correctly, then this new hook allows for "decorating" these methods with span automatically.

[RogerHYang]

Yes, all subclasses will have these methods decorated automatically.

[logan-markewich]

Lets add a docstring to this method to explain what's happening in here for future devs

[RogerHYang]

added

[logan-markewich]

Can we add a comment for what this is doing? I actually don't quite get what is happening here haha

[RogerHYang]

Added.

Screenshots below show the difference before/after the pass-through.

before

after

[nerdai]

Lgtm, @RogerHYang -- thanks!