Environment

Overview

The environment feature allows you to specify which environment your traces are coming from. This is useful for separating traces from different environments in "development", "staging", "production", or "testing".

Configure Environment

You can configure the environment with the CONFIDENT_TRACE_ENVIRONMENT environment variable.

$
export CONFIDENT_TRACE_ENVIRONMENT="staging" 

Alternatively, you can set the environment directly in code:

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

The environment can be either "production", "staging", or "development", and helps you identify where your traces are coming from.