Metadata-Version: 2.3
Name: trainloop-llm-logging
Version: 0.7.2
Summary: TrainLoop LLM Logging SDK for data collection
Author: Mason Pierce
Author-email: masonpierce@trainloop.ai
Requires-Python: >=3.9,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: fsspec (>=2023.1.0)
Requires-Dist: pyyaml (>=6.0,<7.0)
Requires-Dist: requests (>=2.31.0,<3.0.0)
Description-Content-Type: text/markdown

# TrainLoop Evals SDK (Python)

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

## Install

```bash
pip install trainloop-llm-logging
```

## Quick example

```python
from trainloop_llm_logging 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](../../README.md) for more details.

