Skip to main content
Flows in LLM Controls are fully serializable and can be saved and loaded from the file system. In this guide, we’ll explore how to import and export flows.

​
Import Flow​

If you’ve already got an LLM Controls JSON file, import it into LLM Controls by clicking on the project name and choosing Import Flow. Flow Video Gi Once imported, your flow is ready to use.
TIPYou can drag and drop LLM Controls files directly from your file system into the LLM Controls window to import a flow, even into the initial LLM Controls splash screen.

​
Export Flow​

The option to export a flow is available in the same menu as shown above. Once exported as JSON, you can import your flow into another LLM Controls instance.

​
LLM Controls JSON file contents​

LLM Controls JSON files contain nodes and edges that describe components and connections, and additional metadata that describes the flow.

​
Nodes​

Nodes represent the components that make up the flow. The ChatInput node is the entry point of the flow. It’s the first node that will be executed. ChatInput-jFwUm is a unique identifier for the node.

​
Edges​

Edges represent the connections between nodes. The connection between the ChatInput node and the OpenAIModel node is represented as an edge: This edge shows that the ChatInput component outputs a Message type to the target node, which is the OpenAIModel node. The OpenAIModel component accepts the Message type at the input_value field.

​
Additional metadata and project information​

Additional information about the flow is stored in the root data object.
  • Metadata and project information, including the name, description, and last_tested_version of the flow.
  • Visual information about the flow defines the initial position of the flow in the workspace.
Notes are like comments to help you understand the flow within the workspace. They may contain links, code snippets, and other information. Notes are written in Markdown and stored as node objects.