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 configuration reference

Understand the node library

Browse the ten registered node types by role in the workflow.

Ragify's editor includes ten types in four categories: Input, Processing, Query, and Output. The node library is a description of the current frontend registry. Node-specific configuration screens may contain additional fields; always use the live editor as the authority for exact field names and defaults.

Input #

Document Loader: represents source material and its entry into the document-processing path.

Processing #

Chunker: represents splitting content into smaller units. Embedder: represents generating vector representations of text.

Query #

Vector Store: represents a store for vector data. Retriever: represents dense similarity search. Hybrid Retriever: represents dense and BM25 search combined through RRF. Reranker: represents cross-encoder re-scoring of retrieved candidates.

Output #

LLM: represents answer generation. Answer / Output: represents the presentation of a response. RAGAS Evaluator: represents answer-quality evaluation.

Reading the node pages #

Each node page states what it represents, where it fits in a graph, design-time guidance, and common mistakes. Node descriptions are conceptual until runtime services exist.