Skip to main content

A framework-agnostic Python library to seamlessly integrate Apache Cassandra with ML/LLM/genAI workloads.

Project description

cassIO

A framework-agnostic Python library to seamlessly integrate Apache Cassandra with ML/LLM/genAI workloads.

Note: this is currently an alpha release.

Users

Step 1: pip install cassio.

Step 2: for example usages and integration with higher-level LLM frameworks such as LangChain, please visit cassio.org.

Step 3: if you need the (experimental) Vector Search capabilities, you'll have to install custom Cassandra drivers on top of the one shipping with the package. Check requirements-dev.txt to find out how to do it.

CassIO developers

Developing

To develop cassio, use the requirements-dev.txt (which also builds the experimental vector support for the Python drivers).

To use the dev version in an integration (e.g. your branch of LangChain),

  • pip install -e . in this cassio repo;
  • pip install -e . in the LangChain cassio branch of this fork;
  • plus any additional requirement files specific to the examples you're running (such as Jupyter).

Publishing

python setup.py sdist bdist_wheel
twine upload dist/*
# (login to PyPI ...)

Unit testing

In a virtualenv with the requirements-dev.txt installed, run:

pytest

(there's not ... much yet in the way of testing).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cassio-0.0.1.tar.gz (9.8 kB view hashes)

Uploaded Source

Built Distribution

cassio-0.0.1-py3-none-any.whl (11.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page