The easiest way to install is via pip and PyPI
pip install txtai
Python 3.8+ is supported. Using a Python virtual environment is recommended.
txtai has the following optional dependencies that can be installed as extras. The patterns below are supported in setup.py install_requires sections.
Note: Extras are provided for convenience. Alternatively, individual packages can be installed to limit dependencies.
Install all dependencies.
pip install txtai[all]
Serve txtai via a web API.
pip install txtai[api]
Interface with cloud compute.
pip install txtai[cloud]
Command line index query console.
pip install txtai[console]
Additional content storage options.
pip install txtai[database]
Topic modeling, data connectivity and network analysis.
pip install txtai[graph]
Additional non-standard models.
pip install txtai[model]
All pipelines - default install comes with most common pipelines.
pip install txtai[pipeline]
More granular extras are available for pipeline categories:
Word vectors, support for sentence-transformers models not on the HF Hub and additional ANN libraries.
pip install txtai[similarity]
All workflow tasks - default install comes with most common workflow tasks.
pip install txtai[workflow]
Multiple dependencies can be specified at the same time.
pip install txtai[pipeline,workflow]
Environment specific prerequisites
Additional environment specific prerequisites are below.
Optional audio transcription requires a system library to be installed
Older versions of Faiss have a runtime dependency on
libomp for macOS. Run
brew install libomp in this case.
Optional dependencies require C++ Build Tools
Install from source
txtai can also be installed directly from GitHub to access the latest, unreleased features.
pip install git+https://github.com/neuml/txtai
A community-supported txtai package is available via conda-forge.
conda install -c conda-forge txtai
Run with containers
Docker images are available for txtai. See this section for more information on container-based installs.