Input/Output
Both traces and spans have inputs and outputs, which you can set dynamically within your application using the update_current_span and update_current_trace function respectively.
Set Trace I/O At Runtime
You can set the input and output of a trace using the update_current_trace function:
Python
import openai
from deepeval.tracing import observe, update_current_trace
@observe()
def llm_app(query: str):
res = openai.ChatCompletion.create(
model="gpt-4o",
messages=[
{"role": "user", "content": query}
]
).choices[0].message["content"]
update_current_trace(input=query, output=res)
return res
llm_app("Write me a poem.")The input and output can be ANY TYPE, and is useful for visualization on the UI (even more so if you’re using conversation threads).
Big disclaimer for threads
HOWEVER, if you are planning to create a thread from the traces (for chatbots, conversations, etc. multi-turn use cases), it is highly recommended that you provide strings instead, where the input will represent the user input, and output representing the LLM generated output. You can also leave out any input or output for consecutive user/LLM behaviors.
You will also need the input and output to run online evaluations on a thread, as these will be used as the turns for a conversational test case.
Set Span I/O At Runtime
You can set the input and output on spans using the update_current_span function.
One thing to note however, is we recommend setting attributes instead of input and output directly on spans that are one of the DEFAULT span types, since DeepEval handles the input and output setting automatically for default span types.
For example, the "retriever" span type expects a string as the input and list of strings as the output, which you might violate if setting I/O yourself. This will decrease the chances that you run into an error.
Python
import openai
from deepeval.tracing import observe, update_current_span
@observe()
def llm_app(query: str):
res = openai.ChatCompletion.create(
model="gpt-4o",
messages=[
{"role": "user", "content": query}
]
).choices[0].message["content"]
update_current_span(input=query, output=res)
return res
llm_app("Write me a poem.")This example is the same as the one for tracing except for the update_current_trace, and that’s not a mistake. You can set input and outputs the same way as you do for traces, and if a trace’s I/O is not set it defaults to the I/O of the root span.
The input and output can be ANY TYPE for custom span types, and is useful for visualization on the UI.