trainloop-llm-logging 0.4.0

TrainLoop Evaluations SDK for data collection and evaluation

TrainLoop Evals SDK (Python)

Automatically capture LLM calls from Python apps so they can be graded later.

Install

pip install trainloop-llm-logging

Quick example

from trainloop_evals import collect, trainloop_tag
collect()  # patch HTTP clients
openai.chat.completions.create(..., trainloop_tag("my-tag"))

Set TRAINLOOP_DATA_FOLDER to choose where event files are written or set data_folder in your trainloop.config.yaml file.

See the project README for more details.