Retrieval icons

The 25 retrieval icons in RAG & Search, described

Agentic RAGagentic-rag

Agentic RAG — the agent decides what to look up next in a retrieval loop.

Context assemblycontext-assembly

Context assembly — the retrieved pieces gathered and composed into one prompt.

Context budgetcontext-budget

A context budget — how much room is left in the window for more tokens.

Context injectioncontext-injection

Context injection — putting extra material into the prompt before the model sees it.

Context overflowcontext-overflow

Context overflow — more tokens than the window will hold, so something gets truncated.

Dense searchdense-search

Dense search — retrieval by embedding vector rather than by matching words.

Metadata filterfilter-metadata

A metadata filter — narrow the candidates by tags or facets before you search.

Filter resultfilter-result

A filter result — what made it through the filter, the matching output.

Hybrid fusehybrid-fuse

Hybrid fuse — keyword and semantic results merged into one ranked list.

Hybrid searchhybrid-search

Hybrid search — keywords and meaning combined, lexical and vector results fused.

HyDEhyde

HyDE — imagine a hypothetical answer and search with its embedding.

Keyword searchkeyword-search

Keyword search — find the literal words themselves, exact text matching.

Multi-hopmulti-hop

Multi-hop — the answer is two documents away, reached by chaining retrievals.

Post-filterpostfilter

Post-filter — search wide, then throw most of the results back.

Pre-filterprefilter

Pre-filter — narrow the candidates first, then search what is left.

Query expandquery-expand

Query expansion — one question broadened into several searches.

RAG pipelinerag-pipeline

A RAG pipeline — retrieve the relevant passages, then generate with what you found.

Retrieverretriever

A retriever — the component that fetches the documents most likely to help answer a query.

Semanticsemantic

Semantic — by what it means rather than what it says, meaning beyond the words.

Semantic searchsemantic-search

Semantic search — find things by what they mean, using vectors and similarity rather than keywords.

Similarity searchsimilarity-search

Similarity search — find what is most like this one, the nearest neighbours.

Sparse searchsparse-search

Sparse search — match the words themselves, lexical and exact.

Step backstep-back

Step-back prompting — ask the bigger, more abstract question first.

Subquestionsubquestion

A subquestion — the big ask cut into pieces that can each be answered.

Vector searchvector-search

Vector search — find the nearest points in embedding space, a k-nearest-neighbour lookup.

In code, each is one import — import { AgenticRag } from "@iconmind/react/icons/agentic-rag" — and the same name in Vue, Svelte, Solid, Preact, React Native, Astro, Blade and Flutter.

Narrow it by tag