baguetter
Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter supports sparse (traditional), dense (semantic), and hybrid retrieval methods.
File Explorer
Download Latest Version (.zip)- action.yml
- _lint.yml
- _release.yml
- _test.yml
- _test_release.yml
- __init__.py
- base.py
- constants.py
- hf_dataset.py
- __init__.py
- eval.py
- __init__.py
- config.py
- fuser.py
- __init__.py
- base.py
- config.py
- faiss.py
- usearch.py
- __init__.py
- index.py
- scoring.py
- __init__.py
- index.py
- __init__.py
- __init__.py
- normalization.py
- stemmer.py
- stopwords.py
- text_processor.py
- tokenizer.py
- __init__.py
- base.py
- bm25.py
- bmx.py
- config.py
- __init__.py
- base.py
- mutli.py
- search_engine.py
- __init__.py
- common.py
- file_repository.py
- model_helpers.py
- numba_utils.py
- numpy_cache.py
- numpy_utils.py
- persistable.py
- sqlite_key_val.py
- __init__.py
- cli.py
- enums.py
- logger.py
- py.typed
- settings.py
- types.py
- eval_loco.py
- eval_aug_mteb.py
- eval_mteb.py
- README.md
- eval.py
- dense_index.ipynb
- embedding_quantization.ipynb
- hf_save_idx.ipynb
- pre_tokenize.ipynb
- reranking.ipynb
- save_idx.ipynb
- eval_test.py
- faiss_test.py
- usearch_test.py
- stemmer_test.py
- stopwords_test.py
- text_normalization_test.py
- tokenizer_test.py
- base_test.py
- model_test.py
- mteb_test.py
- __init__.py
- index.py
- text_preprocessor.py
- __init__.py
- numba_utils_test.py
- .gitignore
- .pre-commit-config.yaml
- conftest.py
- LICENSE
- Makefile
- pyproject.toml
- README.md
- README_CN.md
- ruff.toml
# Installation Guide
git clone https://github.com/mixedbread-ai/baguetter
Downloads the entire project code from GitHub to your computer.
cd baguetter
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install baguetter
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install baguetter
Installs the package published on PyPI directly โ no need to clone the source.
python -m pip install -e ".[dev]"
Installs the Python libraries listed in requirements.txt (or similar).
Pulled directly from this repo's README.
4. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make
Compiles the code based on the generated build configuration to produce an executable.