Build with Design
Design is aiXplain’s UI tool for building AI pipelines. Watch our overview video for an introduction.
Check out the How to build a pipeline SDK guide for building pipelines programmatically.
1. Input & Output nodes
The input and output nodes allow you to pass inputs to your pipelines and receive outputs.
- Every pipeline requires at least 1 input node and 1 output node.
- Connect input nodes to asset parameters.
2. Decision nodes
The decision node allows or prevents data from passing through it based on criteria.
3. Router nodes
The router node allows pipelines to have multimodal inputs. It does so by detecting the input type, whether it’s text, audio, and so on, and routes it accordingly.
4. Metric nodes
The metric node can be populated with a Metric asset. It accepts input-target pairs and outputs a score, allowing you to test the performance of your models and pipelines.
5. Segmentors & Reconstructors
Segmentors and Reconstructors are two terms that reflect the behavior of some aiXplain models, and as the names suggest, Segmentors segment your data into segments, and Reconstructors reconstruct them back together.
6. Script nodes
Learn to use script nodes in our How to use Script Nodes SDK guide.