RedisAI Python Client

onnx, python-client, redisai, tensor, torch
pip install redisai==1.3.0



redisai-py is the Python client for RedisAI. Checkout the documentation for API details and examples


  1. Install Redis 5.0 or above
  2. Install RedisAI
  3. Install the Python client
$ pip install redisai
  1. Install serialization-deserialization utility (optional)
$ pip install ml2rt


  1. Assuming you have virtualenv installed, create a virtualenv to manage your python dependencies, and activate it. `virtualenv -v venv; source venv/bin/activate`
  2. Install [pypoetry]( to manage your dependencies. `pip install poetry`
  3. Install dependencies. `poetry install --no-root`

[tox]( runs all tests as its default target. Running tox by itself will run unit tests. Ensure you have a running redis, with the module loaded.


Prior to submitting a pull request, please ensure you've built and installed poetry as above. Then:

  1. Run the linter. `tox -e linters.`
  2. Run the unit tests. This assumes you have a redis server running, with the [RedisAI module]( already loaded. If you don't, you may want to install a [docker build]( `tox -e tests`

RedisAI example repo shows few examples made using redisai-py under python_client folder. Also, checkout ml2rt for convenient functions those might help in converting models (sparkml, sklearn, xgboost to ONNX), serializing models to disk, loading it back to redisai-py etc.