After spending some months working on the Pipeless open-source framework, today I bring something new and really cool: Pipeless Agents
Imagine providing a video source and directly processing a data stream that represents what is happening on the video, just like when you work with normal data. Each payload represents an event on the video, an object, or whatever you are interested in.
Sounds good, right? Well, it is now possible.
With Pipeless Agents you can create any kind of automation based on real-time video inputs. You do not need infrastructure, you do not need to label data or train models. You connect a git repository with your agent logic and the rest is handled for you.
So, what does that agent logic look like?
It is just a script that processes the data extracted from your video sources, like the following:
As you can see, with just two lines of code you can define the agent. The first imports the SDK and the second is a for loop that will run for every data structure extracted from the video. Inside the loop, you can do whatever you want. You can send emails or Slack notifications, you can call some webhooks, you can stop a production line, you can analyze and store the data in a database, ... There are no restrictions, the only limit is your imagination!
But, how does the agent know the kind of data/events you want?
We use some filters for that. Every filter focuses on exporting specific data or detecting a specific event. When you connect your video sources you also specify the list of filters that you want to apply to the video and every filter produces a well-defined data structure, which is what your agent receives.
Right now, we are providing some pre-defined filters such as object detection, but we are working to allow you to define your custom filters. Let us know if there is some specific filter you would like to see!
How do you get started?
Just go to https://agents.pipeless.ai and create your first agent!
Also don’t forget to send us your feedback, we love to hear your thoughts!
Hope you enjoy it!
Top comments (0)