Skip to article
/ docs

Search documentation

Popular starting points. Search all 37 articles.

  • Get startedProduct availability and preview limitationsUnderstand what works in the frontend and which product capabilities are not connected yet.
  • Get startedBuild your first RAG pipelineBuild and inspect your first seven-node Basic RAG graph and learn what validation means.
  • Build pipelinesBasic RAG and Hybrid Search templatesCompare Ragify's two starting graphs and decide which pattern to explore.
  • Node referenceUnderstand the node libraryBrowse the ten registered node types by role in the workflow.

↑ ↓ to navigate · Enter to open · Esc to close

Back to Ragify ↗
On this page

Documentation

Frontend preview

Understand the pipeline editor

Explore the canvas, node library, toolbar, and configuration workflow.

The pipeline editor is Ragify's main design surface. It shows nodes, directional connections, editing actions, and validation feedback in one place. Most editing happens on the canvas, while node-specific settings open in a modal rather than a permanent side panel.

Canvas and graph #

Nodes represent stages of a RAG workflow. Connectors show the intended order of information flow. You can arrange nodes to make the pipeline easier to inspect and use editing controls supplied by the interface. The current graph model is intentionally constrained to one linear chain and one retrieval strategy.

Node library #

The library contains ten supported types. They are grouped into Input, Processing, Query, and Output categories. Use node search to locate a component by name or purpose.

Configuration dialogs #

Select a node to inspect its configuration. The modal keeps the full canvas visible behind the dialog and focuses the editing task on a single stage. Only documented visible controls should be treated as implemented; configuration UI is not a live provider connection.

Validation feedback #

Use graph validation to check supported structural and configuration constraints. If a graph is invalid, use the reported guidance to repair the design. Validation is a frontend check, not a trial run of ingestion or retrieval.

Add and connect nodes, Configure individual nodes, Validate a pipeline.