trainloop-evals-sdk 0.1.11

TrainLoop Evaluations SDK for data collection and evaluation

TrainLoop Evals SDK

A lightweight Python SDK for collecting, submitting, and evaluating LLM responses with TrainLoop.

Installation

pip install trainloop-evals-sdk

Usage

Data Collection

from trainloop_evals import collect

# Set this up during the initialization of your application
# to collect data from all LLM calls
collect()

# Annotate llm calls with the trainloop_tag parameter
# the sdk will intelligently remove the parameter and collect information about the llm call
import openai

openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "2+2"}],
    trainloop_tag="math.addition"
)

Configuration

The SDK can be configured using environment variables:

• TRAINLOOP_DATA_FOLDER: Directory where the registry file will be saved. If this is not set, collect() becomes a no-op.

Advanced Usage

See the documentation for complete API reference.