Anthony Cavin

Machines often send several measurements at once. A controller might send a CSV packet every 200 milliseconds, with several readings in each packet. ReductStore stores each packet as a timestamped record, without splitting it into individual measurements. This keeps the original packets intact, even as the number of records grows.

Later, you might want to find readings above a threshold, calculate an average over a time window, or combine the packets into a Parquet file. Rather than downloading all the raw data and processing it in your application, you can use ReductSelect to process the records directly on the server.

Anomalib makes it relatively easy to train an anomaly detection model on your own images. But once you want to use it in production, you also need to handle inference, evaluate predictions, and keep track of the images that triggered them.

In this tutorial, we'll use anomalib to train and run an anomaly detection model in Python. Then we'll look at how to store images alongside their anomaly scores, so you can review detections and use them for future training.

ROS 1 Noetic reached end of life in May 2025, but a lot of robots still run on it. Recording data from them usually means rosbag files, or a custom recording node that you have to maintain yourself.

ReductBridge is another way to do it. It subscribes to topics on a ROS 1 master and stores each message it receives in ReductStore as a record, so you can query by time and by label later. It can also use the timestamp from the message header instead of the time the message arrived.

In this tutorial we'll record a camera topic and an IMU topic, set a retention limit, and read the data back with the ReductStore CLI and the Python SDK.