Metadata-Version: 2.4
Name: batchedllm
Version: 0.2.0
Summary: like itertools.batched but for calling LLM
Project-URL: repository, https://github.com/batchedllm/batchedllm
Author-email: Danil Kireev <nenil@nenil.dev>, Daniil Larionov <rexhaif.io@gmail.com>
License-Expression: MIT
Keywords: LLM,batched
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Utilities
Requires-Python: >=3.12
Requires-Dist: tqdm>=4.67.3
Description-Content-Type: text/markdown

# BatchedLLM
like itertools.batched but for calling LLM

[![Ruff and Ty and PyTest checks](https://github.com/batchedllm/batchedllm/actions/workflows/lint_and_test.yml/badge.svg)](https://github.com/batchedllm/batchedllm/actions/workflows/lint_and_test.yml)

## Example
Run the OpenAI speed comparison example with `uv --script`:

```sh
OPENAI_BASE_URL=<url or https://api.openai.com/v1> OPENAI_MODEL=<model or gpt-5-nano> OPENAI_API_KEY=sk-... uv run --script examples/openai_speed.py
```
