Tags | Confident AI Docs

Overview

Unlike metadata, which can contain complex structured data, tags are simple string labels that make it easy to group related traces together, and cannot be applied to spans.

Tags provide a simple way to categorize and filter your traces in Confident’s observatory.

Add Tags to Traces

Tags are applied at the trace level, making them visible for all spans within that trace.

Python

TypeScript

main.py

1 from deepeval.tracing import observe, update_current_trace
2 from openai import OpenAI
3 
4 client = OpenAI()
5 
6 @observe(type="agent")
7 def llm_app(query: str):
8     update_current_trace(tags=["Causal Chit-Chat"])
9 
10     return client.chat.completions.create(
11         model="gpt-4o",
12         messages=[{"role": "user", "content": query}]
13     ).choices[0].message.content
14 
15 llm_app("Write me a poem.")

1	from deepeval.tracing import observe, update_current_trace
2	from openai import OpenAI
3
4	client = OpenAI()
5
6	@observe(type="agent")
7	def llm_app(query: str):
8	update_current_trace(tags=["Causal Chit-Chat"])
9
10	return client.chat.completions.create(
11	model="gpt-4o",
12	messages=[{"role": "user", "content": query}]
13	).choices[0].message.content
14
15	llm_app("Write me a poem.")