Installation¶
Requirements¶
- Python 3.10 or later. CI tests 3.10, 3.11, 3.12 and 3.13.
- A GPU is optional. Hosted providers and small local models run on CPU; larger local models are practical only on a GPU.
Install from PyPI¶
Run laiser setup once before extracting. It downloads the package's taxonomy bundles from GitHub Releases,
checks their integrity, and prepares the alignment embedding model. No provider API key is needed for setup.
The taxonomy bundles total about 125 MiB compressed and are cached under ~/.cache/laiser by default.
Set LAISER_CACHE_DIR to use a different taxonomy cache directory. The embedding model uses the
Hugging Face cache, which can be set with HF_HOME. Use the same cache settings for setup and extraction.
Re-running setup reuses the prepared files.
GPU inference with vLLM¶
The gpu extra adds vLLM for faster local inference on CUDA devices, plus
bitsandbytes and accelerate, which LAiSER uses to load a model in 8-bit when vLLM cannot. Check that
PyTorch can see your GPU:
Local GGUF models with llama.cpp¶
To run a quantized GGUF model through llama.cpp, install its Python bindings separately:
See Model providers for how to point LAiSER at the model file.
Install from source¶
git clone https://github.com/LAiSER-Software/extract-module.git
cd extract-module
pip install -e ".[dev]"
The dev extra adds the test and lint tooling used in CI.
The checkout includes the taxonomy files. Run laiser setup to prepare its alignment embedding model
ahead of time as well.
Language models¶
Setup prepares the taxonomy data and the embedding model used for alignment. If you choose a local language model for extraction, that model has its own download. Hosted providers such as Gemini still need network access when extracting from text.