Comment on page
Build custom AI workflows using drag-and-drop nodes.
Pipelines execute the core logic of workflows built using VectorShift. They can contain inputs, outputs, and multiple processing steps in between, all of which can be connected together using a drag-and-drop interface. The Pipeline Builder section goes into more detail regarding how Pipelines are structured.
- 1.The "Build" button gives you access to the Pipeline builder
- 2.The "Run" button opens up a "form-like" interface for you to give inputs and receive outputs from the Pipeline
- 3.The "Cost" column gives the cost in credits to running each of the Pipelines one time
To view Pipelines that you have imported from the Marketplace, click "Imported Pipelines" from the pull down menu on the top right.
To move a pipeline from "Imported Pipelines" to the "My Pipelines" page where they can be edited, click on the 3 dots on the right hand side of the pipeline and click "Add to My Pipelines"
From the pull down menu, you can also view Pipelines that are shared with you if you are in an organization or historical runs of a Pipeline you have previously run.
Delete a Pipeline by checking a Pipeline and clicking "Delete".
The Pipeline builder can be accessed by clicking the "Build" button on the Pipelines tab.
Every Pipeline is composed of nodes and edges. Nodes represent the individual units of functionality that a Pipeline executes, such as retrieving data from various Data Loaders, processing inputs using a large language model (LLM), or formatting Text. Edges are the connections between nodes, allowing you to connect the output of one node to the input of a different node.
Every node input/output has a given type, and edges can only be added between compatible types. You will not be able to create edges that result in incompatible types unless you disable the Enforce Type Safety option on the top-right of the Pipeline builder. Sometimes, creating an edge will give you a Warning, which indicates that the types at either end of the edge may be compatible sometimes but not in all cases. You can select Hide Warnings if you want to remove these messages.
Example Pipeline in the Pipeline Builder
You can run a Pipeline directly through the Pipeline builder by clicking the Run Pipeline button in the top-right, filling out the relevant inputs and outputs, and clicking Run. You will be able to see the intermediate outputs from the nodes as the Pipeline runs.
You can view and edit the name, description, and shared users associated with the Pipeline on the Edit Information tab. You can also save the Pipeline from here.