Dictionary
Retrieval
Selecting the most relevant chunks for a query before generation.
1 min readupdated 2026-07-04
/ quick answer
Retrieval is the R in RAG: given a query, score candidate chunks by similarity (vector, keyword, or hybrid) and return the top-k to inject into the prompt. Selecting the most relevant chunks for a query before generation.
Selecting the most relevant chunks for a query before generation. Retrieval is the R in RAG: given a query, score candidate chunks by similarity (vector, keyword, or hybrid) and return the top-k to inject into the prompt. In practice: Query 'refund policy' returns the 3 highest-similarity chunks from the help-center index. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
Retrieval is the R in RAG: given a query, score candidate chunks by similarity (vector, keyword, or hybrid) and return the top-k to inject into the prompt.
Example
Query 'refund policy' returns the 3 highest-similarity chunks from the help-center index.
Related Workflows
Related Tool Stacks
/ frequently asked
What is Retrieval?
Retrieval is the R in RAG: given a query, score candidate chunks by similarity (vector, keyword, or hybrid) and return the top-k to inject into the prompt.
What is an example of Retrieval?
Query 'refund policy' returns the 3 highest-similarity chunks from the help-center index.
Why does Retrieval matter for AI and automation?
Selecting the most relevant chunks for a query before generation. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.
↳ connected nodes
Workflow↳ linked
Build an Internal Knowledge Bot
Ship a Slack bot that answers questions from your company docs.
Tool Stack↳ linked
RAG Starter Stack
Minimum viable stack to ship a production RAG chatbot.
Workflow↳ linked
Context Window Optimization Workflow
This workflow outlines steps to optimize the information fed into an LLM's finite context window, ensuring maximal relevance and efficiency while managing token limits.
Dictionary↳ linked
Contextual Compression
Contextual compression is a technique used to reduce the size of the input context for a Large Language Model (LLM) while retaining its most relevant information, typically by summarizing or filtering.
Dictionary↳ linked
RAG (Retrieval-Augmented Generation)
Inject external knowledge into an LLM at query time.
Dictionary↳ linked
Agentic RAG
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.