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

Welcome to Ragify

Learn what Ragify is, explore its visual pipeline builder, and find the right place to begin.

Get startedBuild your first RAG pipelineBuild and inspect your first seven-node Basic RAG graph and learn what validation means.Build pipelinesUnderstand the pipeline editorExplore the canvas, node library, toolbar, and configuration workflow.Node referenceUnderstand the node libraryBrowse the ten registered node types by role in the workflow.Get startedProduct availability and preview limitationsUnderstand what works in the frontend and which product capabilities are not connected yet.Help & referenceTroubleshootingResolve common design-time questions and distinguish interface previews from backend failures.API & deploymentAPI and deployment availabilityUnderstand the future API direction without mistaking a mock endpoint for a live service.

Ragify is a visual environment for designing Retrieval-Augmented Generation (RAG) pipelines. Instead of reasoning about every connection from separate configuration files, you can arrange processing, retrieval, and generation components on a canvas and inspect how they fit together.

The current Ragify frontend is focused on pipeline design. It offers node insertion and configuration, graph validation, guided onboarding, and starting templates. It also includes workspace screens for Documents, Runs, and API Access, but those screens do not represent a connected backend.

Where to start #

  • Build your first pipeline: Open the Basic RAG template, inspect its nodes, and validate the graph. Read Build your first RAG pipeline.
  • Explore the visual editor: Learn to add nodes, make connections, and configure each stage. Read Understand the pipeline editor.
  • Find a node: Browse descriptions of all ten registered node types. Read Node reference.
  • Understand the limitations: Learn which controls are interactive and which show previews of future services. Read Product availability.

What you can design #

A typical starting pipeline contains Document Loader, Chunker, Embedder, Vector Store, Retriever, LLM, and Answer / Output. The Hybrid Search template adds a Hybrid Retriever and a Reranker in place of the standard retrieval stage.

Before you continue #

Graph validity means the editor has accepted the structure and configuration it can inspect. It does not mean that documents have been ingested, a model has run, or a query endpoint has been deployed.

Next: Build your first RAG pipeline.