Metadata-Version: 2.4
Name: jammi-server
Version: 0.28.0
Summary: CPU build of the Jammi engine server — `jammi-server` console binary, pip-installable
Project-URL: Homepage, https://github.com/f-inverse/jammi-ai
Project-URL: Documentation, https://f-inverse.github.io/jammi-ai/
Project-URL: Repository, https://github.com/f-inverse/jammi-ai
Project-URL: Bug Tracker, https://github.com/f-inverse/jammi-ai/issues
Author: F-Inverse
License: Apache-2.0
Keywords: embeddings,fine-tune,inference,server,vector-search
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Rust
Classifier: Topic :: Database
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# jammi-server

CPU build of the Jammi engine server, packaged as a pip-installable wheel that
ships the compiled `jammi-server` binary behind a `jammi-server` console script.

```console
pip install jammi-server
jammi-server --help
```

The wheel bundles a prebuilt Linux `x86_64` binary (manylinux_2_28 glibc floor)
compiled with the broker and cloud-storage backends. For GPU-accelerated
inference and fine-tuning, install `jammi-server-cu12` instead — it provides the
same `jammi-server` command built against the CUDA backend.
