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

Current reference

Product availability and preview limitations

Understand what works in the frontend and which product capabilities are not connected yet.

Ragify's current frontend includes functional visual design tools and several interface previews. It is important to distinguish a configurable graph from an executable, deployed RAG service.

Available in the current frontend #

  • Interactive node-based pipeline editor with connection and editing controls.
  • Ten registered node types grouped as Input, Processing, Query, and Output.
  • Node configuration interfaces and a frontend graph validator.
  • Basic RAG and Hybrid Search starting templates.
  • Guided onboarding for selecting a goal, naming a workspace, choosing a template, and optionally selecting documents.
  • Dark, light, and system theme preferences.
  • Workspace previews including Dashboard, Documents, Runs, and API Access.

Frontend-only or illustrative behavior #

  • Graph state is scoped to the active editor session; it is not saved to a backend database.
  • Document selection uses metadata in the preview; file bytes are not ingested or stored by a backend.
  • Run history and analytics visuals are sample or preview information.
  • API Access snippets and pipeline-query endpoints are illustrative contracts, not operational services.
  • Provider configuration dialogs do not transmit provider credentials to a backend.

Not implemented yet #

  • Authentication and backend authorization.
  • Persistent pipeline save/load and version history.
  • Actual ingestion, embedding jobs, vector-store operations, retrieval, and LLM execution.
  • Server-side run history and production monitoring.
  • Deployed pipeline endpoints and operational API key creation, rotation, and revocation.
  • Production billing or service guarantees.

Why this matters #

You can build and inspect a graph today, but do not use a frontend validation success message as evidence that a pipeline is live. Do not place genuine credentials in a preview form or public URL. The documentation marks planned integrations separately so examples are never mistaken for functional deployment instructions.

Related: Validate a pipeline; API and deployment availability.