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

Configurable frontend node; hybrid search execution planned

Hybrid Retriever

Represent combined dense and keyword retrieval with rank fusion.

Category: Query. Registry label: Hybrid Retriever. Registry subtitle: Dense + BM25 with RRF fusion.

Purpose #

Hybrid retrieval combines candidate results from semantic similarity and keyword-based search. Reciprocal rank fusion (RRF) is a conceptual technique for combining result rankings from these retrieval methods.

Position in the graph #

Vector Store → Hybrid Retriever → Reranker

Design guidance #

Use the Hybrid Search template when exploring this strategy. The hybrid retriever replaces the basic dense Retriever stage in the eight-node template. Follow it with a Reranker in the provided structure.

Current limitation #

The node represents a planned retrieval strategy; no BM25 index, rank fusion job, or dense search runs in the current frontend.

Reranker, Templates.